INDEX

Explanations

references to historical periods or epochs

oai_token-act-pair · gpt-3.5-turbo

references to different historical eras

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

 drawer

-0.76

acts

-0.75

atem

-0.72

portion

-0.71

acted

-0.68

amina

-0.68

lations

-0.66

pel

-0.65

kie

-0.63

Eva

-0.63

POSITIVE LOGITS

icals

0.90

era

0.90

UTC

0.82

 epoch

0.82

Era

0.79

icity

0.78

osaurs

0.76

 nostalg

0.76

hetti

0.76

 Frieza

0.71

Activations Density 0.022%

references to historical periods or epochs

references to different historical eras

No Comments

No Known Activations