INDEX

Explanations

words related to government officials, legislation, and accountability

oai_token-act-pair · gpt-3.5-turbo

references to specific television or media series

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

-->

-0.73

chio

-0.72

 guiActiveUn

-0.67

emort

-0.65

alogue

-0.62

thur

-0.61

âĢ¢âĢ¢âĢ¢âĢ¢

-0.60

 Guilty

-0.60

////

-0.60

BIL

-0.59

POSITIVE LOGITS

assetsadobe

1.04

wart

0.76

abit

0.70

scenes

0.69

 Macy

0.68

wired

0.67

mong

0.67

0.66

iday

0.66

undreds

0.64

Activations Density 0.066%

words related to government officials, legislation, and accountability

references to specific television or media series

No Comments

No Known Activations