INDEX

Explanations

keywords related to segmented parts or sections within a larger context

oai_token-act-pair · gpt-3.5-turbo

references to specific segments or categories in a context

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

 opio

-0.79

 lett

-0.69

CHA

-0.66

 IMAGES

-0.65

ullivan

-0.63

 realism

-0.62

 father

-0.62

 brink

-0.61

 Angels

-0.61

 Mellon

-0.61

POSITIVE LOGITS

ation

1.12

ated

0.94

arily

0.91

ed

0.91

naire

0.89

eston

0.84

ational

0.83

arse

0.83

nel

0.83

als

0.80

Activations Density 0.028%

keywords related to segmented parts or sections within a larger context

references to specific segments or categories in a context

No Comments

No Known Activations