INDEX

Explanations

words related to different parts of the body, particularly emotional or physical sensations such as heart, palms, stomach, ears, head, mind, body, mouth

oai_token-act-pair · gpt-3.5-turbo

body-related sensations and emotional responses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vaj

-0.65

 Yanuk

-0.65

 Byrne

-0.65

ãĤ¤ãĥĪ

-0.65

 Virt

-0.65

 Leone

-0.64

 Juven

-0.62

È

-0.61

 Salv

-0.61

arenthood

-0.60

POSITIVE LOGITS

ache

0.79

 cursor

0.76

 smelled

0.72

pan

0.72

isp

0.71

shake

0.71

iest

0.71

 stake

0.71

 selves

0.70

 counterpart

0.69

Activations Density 0.207%

words related to different parts of the body, particularly emotional or physical sensations such as heart, palms, stomach, ears, head, mind, body, mouth

body-related sensations and emotional responses

No Comments

No Known Activations