INDEX

Explanations

mention any form of visual content description or caption

oai_token-act-pair · gpt-3.5-turbo

bullet points or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

son

-0.64

hift

-0.63

bda

-0.61

 blackout

-0.60

creen

-0.58

 bearer

-0.58

 laund

-0.58

 mans

-0.57

hal

-0.57

 artificially

-0.56

POSITIVE LOGITS

 CONTIN

0.82

=-

0.79

 +---

0.76

======

0.75

 WATCHED

0.73

--------------------------------------------------------

0.72

oiler

0.72

 Chapters

0.71

--------------------

0.71

=~=~

0.70

Activations Density 0.064%

mention any form of visual content description or caption

bullet points or lists

No Comments

No Known Activations