INDEX

Explanations

words related to railroad tracks

oai_token-act-pair · gpt-3.5-turbo

references to railway tracks

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

the word "tracks"

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ALLY

-0.65

 International

-0.61

 Islanders

-0.61

Iro

-0.60

 Marlins

-0.59

 Kinnikuman

-0.59

Cos

-0.59

 Blizz

-0.59

aples

-0.58

Mi

-0.57

POSITIVE LOGITS

 tracks

1.35

 Tracks

1.22

tracks

1.11

heet

1.05

track

0.95

pace

0.89

schild

0.86

geist

0.85

 track

0.84

cape

0.81

Activations Density 0.010%

words related to railroad tracks

references to railway tracks

the word "tracks"

No Comments

No Known Activations