INDEX

Explanations

references to the concept of "upside."

oai_token-act-pair · gpt-3.5-turbo

references to potential benefits or positive attributes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãģ®éŃĶ

-0.96

ãģ®å®

-0.83

naire

-0.81

ocal

-0.77

ocally

-0.76

tein

-0.74

nance

-0.71

ions

-0.70

Rush

-0.69

sonian

-0.69

POSITIVE LOGITS

 upside

1.33

 srfAttach

0.90

 blind

0.76

olicy

0.76

ï¸

0.70

 facing

0.69

vable

0.68

 ceiling

0.68

 handc

0.67

 heel

0.67

Activations Density 0.008%

references to the concept of "upside."

references to potential benefits or positive attributes

No Known Activations