INDEX

Explanations

phrases related to specifying, indicating, or emphasizing specific details or actions

oai_token-act-pair · gpt-3.5-turbo

action verbs indicating declarations or stipulations

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

talk

-0.73

Tonight

-0.66

 encount

-0.64

Recently

-0.64

think

-0.64

TPPStreamerBot

-0.63

 maneu

-0.63

bite

-0.62

phe

-0.61

 hyster

-0.61

POSITIVE LOGITS

CLUD

0.79

 include

0.69

 guarantees

0.69

tained

0.65

 invalid

0.64

 continuity

0.64

htaking

0.63

 outlines

0.63

 encompass

0.62

 provisions

0.62

Activations Density 0.548%

phrases related to specifying, indicating, or emphasizing specific details or actions

action verbs indicating declarations or stipulations

No Comments

No Known Activations