INDEX

Explanations

images or photographs mentioned in texts

oai_token-act-pair · gpt-3.5-turbo

references to specific images or photos

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

wcs

-0.82

 levied

-0.81

hement

-0.78

nw

-0.76

 depended

-0.75

ãĤ¦ãĤ¹

-0.74

ItemTracker

-0.71

oslav

-0.71

alties

-0.70

 relied

-0.70

POSITIVE LOGITS

 footage

0.75

 images

0.72

 sorts

0.70

RTX

0.70

 celebrities

0.70

him

0.70

tnc

0.69

 what

0.68

 naked

0.68

 nudity

0.66

Activations Density 0.145%

images or photographs mentioned in texts

references to specific images or photos

No Comments

No Known Activations