INDEX

Explanations

names of people or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tumblr

-0.65

 clubhouse

-0.59

 Presidents

-0.53

=]

-0.51

 chicks

-0.51

 Disneyland

-0.51

 undermin

-0.51

ModLoader

-0.51

 womb

-0.50

 Rebels

-0.50

POSITIVE LOGITS

jit

0.78

jen

0.73

berto

0.72

Ã¡n

0.71

 Doyle

0.70

ÅĤ

0.69

sey

0.69

Hos

0.69

Ay

0.68

 Nguyen

0.67

Activations Density 0.657%

names of people or organizations

proper nouns, particularly names and titles

No Comments

No Known Activations