INDEX

Explanations

pronouns and reflexive pronouns referring to oneself or others

oai_token-act-pair · gpt-3.5-turbo

references to self and personal agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Alger

-0.68

 Vine

-0.66

 Clover

-0.64

 Noon

-0.64

 Newspaper

-0.62

Mub

-0.61

 Syndicate

-0.61

 Lawyers

-0.60

PBS

-0.59

RIS

-0.59

POSITIVE LOGITS

selves

0.89

icz

0.68

 worshipped

0.67

ãĥķ

0.67

 selves

0.64

abl

0.64

çīĪ

0.63

ãĤĭ

0.63

anship

0.62

åĤ

0.62

Activations Density 0.038%

pronouns and reflexive pronouns referring to oneself or others

references to self and personal agency

No Comments

No Known Activations