INDEX

Explanations

characters from a non-English alphabet

oai_token-act-pair · gpt-3.5-turbo

unusual or non-standard characters and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Sands

-0.72

WARD

-0.71

 Perkins

-0.71

CLASSIFIED

-0.69

 Carib

-0.68

izable

-0.67

stocks

-0.67

 Mandela

-0.66

ified

-0.65

 Dragonbound

-0.65

POSITIVE LOGITS

ĥ

1.53

ķ

1.45

Ĵ

1.45

ī

1.42

İ

1.42

ħ

1.42

Ľ

1.40

Ģ

1.40

ĺ

1.40

ı

1.39

Activations Density 0.016%

characters from a non-English alphabet

unusual or non-standard characters and symbols

No Comments

No Known Activations