INDEX

Explanations

phrases indicating restriction or limitation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exclusivity or restrictions related to specific groups or contexts

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

Negative Logits

etheless

-0.75

asc

-0.74

acter

-0.74

esh

-0.73

plus

-0.69

christ

-0.68

assi

-0.67

fortunately

-0.65

 syndrome

-0.62

inker

-0.61

POSITIVE LOGITS

arde

0.73

 cosmetic

0.72

 females

0.69

 males

0.68

 aesthetic

0.68

 superficial

0.66

 geographic

0.64

 geographical

0.64

 aesthetics

0.63

 areas

0.63

Activations Density 0.319%

phrases indicating restriction or limitation

phrases indicating exclusivity or restrictions related to specific groups or contexts

No Known Activations