INDEX

Explanations

words with unusual characters, potentially indicating a language-specific or encoded text

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

baugh

-0.79

 mathemat

-0.72

espie

-0.72

iary

-0.68

notes

-0.66

essert

-0.66

 GOODMAN

-0.63

 Sparkle

-0.63

 succession

-0.62

 Zucker

-0.60

POSITIVE LOGITS

ÏĦ

1.07

é¾įåĸļå£«

1.04

½

0.87

ĥ

0.85

Ùħ

0.83

ï¸ı

0.83

hea

0.81

ãĥĺ

0.81

Ī

0.80

Ø±

0.80

Activations Density 0.010%

words with unusual characters, potentially indicating a language-specific or encoded text

specific characters or symbols in the text

No Comments

No Known Activations