INDEX

Explanations

images or visuals referenced as part of content or discussion

oai_token-act-pair · gpt-3.5-turbo

mentions of screenshots

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vet

-0.77

ternity

-0.76

doms

-0.76

mand

-0.74

iott

-0.73

bos

-0.73

neg

-0.72

sen

-0.72

ofi

-0.71

 unregulated

-0.70

POSITIVE LOGITS

reenshot

1.18

 screenshots

1.13

 screenshot

1.10

reenshots

1.01

Screenshot

0.97

 Thumbnails

0.84

photos

0.82

 PHOTO

0.80

 thereof

0.76

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.75

Activations Density 0.012%

images or visuals referenced as part of content or discussion

mentions of screenshots

No Comments

No Known Activations