INDEX

Explanations

a dependency or connection between different pieces of information

oai_token-act-pair · gpt-3.5-turbo

references to claims, allegations, or narratives involving deception or misinformation

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

vironments

-0.62

 partName

-0.60

cour

-0.59

natureconservancy

-0.58

ofi

-0.57

ggles

-0.56

ependence

-0.56

antage

-0.55

uitive

-0.52

 imposes

-0.52

POSITIVE LOGITS

 Bulgar

0.72

 prostitutes

0.67

nikov

0.67

 wrong

0.66

 improperly

0.65

 inappropriately

0.64

 somew

0.63

 beforehand

0.60

 illegally

0.59

lyak

0.59

Activations Density 1.487%

a dependency or connection between different pieces of information

references to claims, allegations, or narratives involving deception or misinformation

No Comments

No Known Activations