INDEX

Explanations

phrases indicating desires or intentions

oai_token-act-pair · gpt-3.5-turbo

expressions of desire or intention

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

aka

-0.67

erver

-0.67

mans

-0.67

inas

-0.67

manship

-0.67

lish

-0.65

iop

-0.63

esc

-0.62

bug

-0.62

minus

-0.62

POSITIVE LOGITS

teness

0.72

 warr

0.70

rison

0.70

 permission

0.69

 revenge

0.65

ãĤ¦ãĤ¹

0.62

 something

0.60

reprene

0.59

ipal

0.59

 originally

0.58

Activations Density 0.064%

phrases indicating desires or intentions

expressions of desire or intention

No Comments

No Known Activations