INDEX

Explanations

words related to opposition or disagreement

oai_token-act-pair · gpt-3.5-turbo

references to opposing viewpoints or positions

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

Interstitial

-0.80

çīĪ

-0.66

 Learns

-0.62

enegger

-0.62

KER

-0.61

 Fork

-0.61

 Carnival

-0.61

 Fallen

-0.60

beit

-0.59

negie

-0.59

POSITIVE LOGITS

onent

1.65

osite

1.63

ortun

1.60

osition

1.51

onents

1.48

osing

1.29

ressive

1.23

ression

1.20

osed

1.17

inion

1.16

Activations Density 0.016%

words related to opposition or disagreement

references to opposing viewpoints or positions

No Comments

No Known Activations