INDEX

Explanations

actions related to looking or observing

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "look" and its variations

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

accompan

-0.66

EStreamFrame

-0.63

ricular

-0.61

MQ

-0.60

ä¹

-0.60

 Trad

-0.60

elsen

-0.60

learning

-0.60

iHUD

-0.59

rss

-0.58

POSITIVE LOGITS

 suspicious

0.78

 alike

0.76

 ashamed

0.76

 suspic

0.75

 favorably

0.74

 bored

0.72

 puzzled

0.71

 invincible

0.71

 incred

0.70

 embarrassed

0.70

Activations Density 0.055%

actions related to looking or observing

instances of the verb "look" and its variations

No Comments

No Known Activations