INDEX

Explanations

instances of a specific action involving physical movement

oai_token-act-pair · gpt-3.5-turbo

references to physical gestures or reactions, particularly shaking heads

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

cliffe

-0.67

 hereafter

-0.66

CLUS

-0.64

LAT

-0.63

INO

-0.63

lain

-0.63

anza

-0.63

rising

-0.62

cour

-0.61

Occup

-0.61

POSITIVE LOGITS

 coin

0.83

 shoulders

0.82

rug

0.80

lid

0.78

 punches

0.75

 dice

0.73

 wrist

0.73

 veil

0.73

 heads

0.71

 socks

0.71

Activations Density 0.140%

instances of a specific action involving physical movement

references to physical gestures or reactions, particularly shaking heads

No Comments

No Known Activations