INDEX

Explanations

statements about being informed or knowledgeable about various topics

oai_token-act-pair · gpt-3.5-turbo

instances of the word "aware" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mini

-0.72

cell

-0.68

OPLE

-0.66

Textures

-0.66

nic

-0.65

packages

-0.62

tele

-0.62

entry

-0.62

mer

-0.62

par

-0.62

POSITIVE LOGITS

ledged

1.16

 aware

1.04

 Aware

0.98

isance

0.90

ness

0.86

ledge

0.84

 NOTICE

0.79

icip

0.79

itaire

0.79

 Lauder

0.75

Activations Density 0.019%

statements about being informed or knowledgeable about various topics

instances of the word "aware" in various contexts

No Comments

No Known Activations