INDEX

Explanations

images or photos mentioned in text

oai_token-act-pair · gpt-3.5-turbo

references to images or pictures in the text

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

indal

-0.76

iates

-0.72

bard

-0.72

gew

-0.72

oing

-0.71

iations

-0.71

iated

-0.70

iating

-0.70

utenberg

-0.67

iance

-0.66

POSITIVE LOGITS

lihood

0.81

orial

0.77

 IMAGES

0.72

 Features

0.72

 Malik

0.68

Picture

0.67

 Fres

0.66

 Towns

0.65

 Islands

0.65

 Feature

0.65

Activations Density 0.016%

images or photos mentioned in text

references to images or pictures in the text

No Comments

No Known Activations