INDEX

Explanations

phrases related to comparisons and contrasts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "what" in relation to various topics or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enburg

-0.74

ster

-0.64

jee

-0.64

por

-0.62

enberg

-0.56

gur

-0.56

ji

-0.56

lich

-0.55

 caveat

-0.55

 largeDownload

-0.54

POSITIVE LOGITS

 happens

1.33

soever

1.32

 happened

1.31

 transpired

1.17

 constitutes

1.12

 else

0.99

 happ

0.93

 constituted

0.89

 separates

0.87

 occurs

0.81

Activations Density 0.109%

phrases related to comparisons and contrasts

instances of the word "what" in relation to various topics or concepts

No Comments

No Known Activations