INDEX

Explanations

words related to various types of stations like train stations, police stations, and space stations

oai_token-act-pair · gpt-3.5-turbo

references to various "stations" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ£

-0.75

aphael

-0.72

assic

-0.71

rahim

-0.71

ornia

-0.71

bestos

-0.69

interstitial

-0.68

Downloadha

-0.66

otos

-0.63

cussion

-0.63

POSITIVE LOGITS

 Station

1.40

Station

1.05

 station

0.98

eering

0.92

station

0.91

 stations

0.91

wagon

0.85

ery

0.83

eers

0.78

mates

0.78

Activations Density 0.007%

words related to various types of stations like train stations, police stations, and space stations

references to various "stations" in different contexts

No Comments

No Known Activations