INDEX

Explanations

specific formatting patterns in documents, specifically identified by colon followed by a digit number

oai_token-act-pair · gpt-3.5-turbo

colloquial or formatted expressions of code examples or structures

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

 reservations

-0.79

 tremend

-0.78

 neighb

-0.72

 reservation

-0.71

 inspector

-0.68

hea

-0.66

odox

-0.66

 investigator

-0.66

 armed

-0.65

 pamph

-0.64

POSITIVE LOGITS

 https

1.16

 http

1.11

https

1.03

http

0.99

 Logged

0.95

 âĹı

0.92

 namely

0.86

ie

0.86

↵↵

0.81

<?

0.81

Activations Density 0.120%

specific formatting patterns in documents, specifically identified by colon followed by a digit number

colloquial or formatted expressions of code examples or structures

No Comments

No Known Activations