INDEX

Explanations

double characters separated by special characters

oai_token-act-pair · gpt-3.5-turbo

sequences of numbers and symbols

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

nesday

-0.92

 destro

-0.88

 redes

-0.74

 undermin

-0.74

 dismantle

-0.71

 consecut

-0.69

 occas

-0.69

ury

-0.69

 herself

-0.68

 themselves

-0.68

POSITIVE LOGITS

 largeDownload

1.00

ccording

0.95

ÂłÂłÂł

0.87

Unless

0.85

ÂłÂłÂłÂłÂłÂłÂłÂł

0.85

ÂłÂłÂłÂł

0.83

================================================================

0.81

âĿ

0.80

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.80

Okay

0.78

Activations Density 0.240%

double characters separated by special characters

sequences of numbers and symbols

No Comments

No Known Activations