INDEX

Explanations

phrases related to negative attitudes or disrespect towards individuals or institutions

oai_token-act-pair · gpt-3.5-turbo

expressions of contempt and mistrust

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Lans

-0.67

 hemor

-0.63

 encyclopedia

-0.63

 advoc

-0.63

Som

-0.62

 stabilization

-0.61

 Explan

-0.61

 Publishers

-0.60

Rum

-0.58

 misunder

-0.58

POSITIVE LOGITS

uous

1.54

uously

1.42

ible

1.04

ful

1.03

fully

0.96

urous

0.95

ibly

0.94

FUL

0.93

orable

0.92

ensible

0.92

Activations Density 0.097%

phrases related to negative attitudes or disrespect towards individuals or institutions

expressions of contempt and mistrust

No Comments

No Known Activations