INDEX

Explanations

words related to companies or business activities

oai_token-act-pair · gpt-3.5-turbo

terms related to health risks and medical conditions

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

Cub

-0.59

 Negro

-0.59

 kingdom

-0.58

¥ŀ

-0.53

 FedEx

-0.53

heastern

-0.53

 Sleeping

-0.53

 gulf

-0.52

Balt

-0.51

West

-0.51

POSITIVE LOGITS

and

0.98

0.90

AND

0.89

0.85

ands

0.77

and

0.74

0.72

andowski

0.70

\":

0.70

Activations Density 0.616%

words related to companies or business activities

terms related to health risks and medical conditions

No Comments

No Known Activations