INDEX

Explanations

specific combinations of non-English characters

oai_token-act-pair · gpt-3.5-turbo

characters resembling special or accented letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oppable

-0.73

 GOODMAN

-0.71

iage

-0.68

ilater

-0.66

ometimes

-0.65

emort

-0.63

 rapt

-0.62

espie

-0.62

ifact

-0.62

 traff

-0.61

POSITIVE LOGITS

Ð½

1.00

¶

1.00

¾

0.99

Ñı

0.92

Ð²

0.91

²

0.87

Ĳ

0.85

±

0.85

lat

0.85

°

0.84

Activations Density 0.012%

specific combinations of non-English characters

characters resembling special or accented letters

No Comments

No Known Activations