INDEX

Explanations

proper nouns related to locations or people

oai_token-act-pair · gpt-3.5-turbo

the word "Mend" and its variations in various contexts

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

ngth

-0.81

Leary

-0.74

ãģĦ

-0.69

 menstru

-0.66

OAD

-0.65

 dism

-0.65

 pneum

-0.63

ked

-0.62

 bowel

-0.61

ãĥīãĥ©ãĤ´ãĥ³

-0.61

POSITIVE LOGITS

enh

1.14

ez

1.05

elson

0.99

ele

0.96

elia

0.95

rov

0.94

ragon

0.93

els

0.92

ell

0.92

iola

0.91

Activations Density 0.030%

proper nouns related to locations or people

the word "Mend" and its variations in various contexts

No Comments

No Known Activations