INDEX

Explanations

names of people, particularly those related to entertainment or sports

oai_token-act-pair · gpt-3.5-turbo

references to individuals with the name "Josh."

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

 Sahara

-0.72

 jung

-0.70

theless

-0.70

heit

-0.69

Ã§a

-0.65

 womb

-0.64

emies

-0.63

vironment

-0.63

 labyrinth

-0.63

sylv

-0.61

POSITIVE LOGITS

iak

0.82

ramer

0.72

akis

0.71

opher

0.70

ovsky

0.69

offer

0.66

henko

0.65

ban

0.65

Han

0.65

iden

0.65

Activations Density 0.241%

names of people, particularly those related to entertainment or sports

references to individuals with the name "Josh."

No Comments

No Known Activations