INDEX

Explanations

phrases related to different professions and roles

oai_token-act-pair · gpt-3.5-turbo

identifiers related to personal roles or identities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

\'

-0.74

ombies

-0.61

videos

-0.61

rists

-0.60

Stars

-0.60

>]

-0.59

odo

-0.57

COMPLE

-0.57

åħī

-0.57

andals

-0.57

POSITIVE LOGITS

 myself

1.29

 yourself

0.91

 oneself

0.89

 ourselves

0.89

 accustomed

0.84

 educator

0.82

 grows

0.78

0.77

we

0.77

 yourselves

0.75

Activations Density 0.114%

phrases related to different professions and roles

identifiers related to personal roles or identities

No Known Activations