INDEX

Explanations

phrases containing the words "eye-catching"

oai_token-act-pair · gpt-3.5-turbo

references to visually striking or attention-grabbing elements

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

hement

-0.81

illet

-0.72

inant

-0.72

>[

-0.68

DN

-0.66

icative

-0.66

igham

-0.65

CK

-0.63

achev

-0.62

 weakest

-0.62

POSITIVE LOGITS

ĸļ

1.14

 Canaver

0.73

beh

0.73

ById

0.73

atically

0.72

oscope

0.71

Witness

0.69

 reflection

0.69

 VIDEOS

0.69

Ĭ±

0.69

Activations Density 0.083%

phrases containing the words "eye-catching"

references to visually striking or attention-grabbing elements

No Comments

No Known Activations