INDEX

Explanations

mentions of articles and publications

oai_token-act-pair · gpt-3.5-turbo

instances of the word "article" and its variations

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

Tokens

-0.73

 Genie

-0.73

ELF

-0.72

Ĭ±

-0.68

 Mouth

-0.65

_>

-0.65

sed

-0.65

ItemImage

-0.64

 Governors

-0.63

AFB

-0.62

POSITIVE LOGITS

 assumes

0.98

 summarizes

0.96

 contains

0.90

 represents

0.89

 illustrates

0.84

 teaches

0.84

 requires

0.83

 cannot

0.82

 describes

0.82

 relies

0.81

Activations Density 0.125%

mentions of articles and publications

instances of the word "article" and its variations

No Comments

No Known Activations