INDEX

Explanations

references to individuals being inducted into various Halls of Fame

oai_token-act-pair · gpt-3.5-turbo

references to the Hall of Fame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

resp

-0.76

selves

-0.74

owicz

-0.65

 Alic

-0.64

cos

-0.64

microsoft

-0.63

eto

-0.61

 Anon

-0.61

 hypers

-0.61

 Gork

-0.61

POSITIVE LOGITS

 Fame

1.15

 honors

0.84

brance

0.82

 induction

0.80

 honored

0.79

 plaque

0.78

 Bowl

0.77

 induct

0.77

rities

0.76

ffen

0.74

Activations Density 0.010%

references to individuals being inducted into various Halls of Fame

references to the Hall of Fame

No Comments

No Known Activations