INDEX

Explanations

references to specific names or surnames

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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´ãĤ¡

-0.72

FUL

-0.71

 prevailing

-0.67

ettel

-0.65

 wheelchair

-0.63

 vested

-0.63

 sten

-0.62

 dysph

-0.59

 flush

-0.59

ãĤ·ãĥ£

-0.58

POSITIVE LOGITS

nih

1.37

Moy

1.32

lio

0.91

esy

0.85

stad

0.84

areth

0.83

lan

0.83

nam

0.80

ety

0.80

sters

0.79

Activations Density 0.009%

references to specific names or surnames

proper nouns, particularly names of individuals

No Comments

No Known Activations