INDEX

Explanations

phrases related to news headlines or article titles

oai_token-act-pair · gpt-3.5-turbo

special characters or punctuation marks within 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

 incorpor

-0.82

 conclud

-0.81

 psychiat

-0.80

 disadvant

-0.79

 obser

-0.75

 behavi

-0.74

 livest

-0.73

 ende

-0.72

 recip

-0.71

 tradem

-0.71

POSITIVE LOGITS

é¾į

0.90

Â°

0.86

âĶģ

0.79

ef

0.78

âĻ

0.78

ãģĨ

0.77

çľ

0.75

Â¯

0.73

Temperature

0.73

verning

0.72

Activations Density 0.167%

phrases related to news headlines or article titles

special characters or punctuation marks within the text

No Comments

No Known Activations