INDEX

Explanations

the word "there" frequently in sentences

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the word "there."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 lymph

-0.65

CJ

-0.60

 wounds

-0.58

FTA

-0.58

 debilitating

-0.58

 bows

-0.57

 favour

-0.56

 Deng

-0.56

 comprom

-0.56

 atro

-0.56

POSITIVE LOGITS

abouts

1.46

tical

0.96

fore

0.87

upon

0.87

tics

0.86

 Somewhere

0.83

inel

0.82

tic

0.79

 somewhere

0.78

FORE

0.77

Activations Density 0.060%

the word "there" frequently in sentences

the repeated mention of the word "there."

No Comments

No Known Activations