INDEX

Explanations

questions or requests being asked

oai_token-act-pair · gpt-3.5-turbo

instances of inquiry or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

axies

-0.69

Rating

-0.67

PsyNetMessage

-0.65

jandro

-0.65

Reviewer

-0.65

 CrossRef

-0.64

yssey

-0.63

 ItemLevel

-0.63

CRIPTION

-0.63

minus

-0.62

POSITIVE LOGITS

 ever

0.89

 anymore

0.72

any

0.71

 consciously

0.70

 actually

0.70

 racially

0.69

 discrimination

0.68

 somehow

0.68

 remotely

0.66

or

0.66

Activations Density 0.358%

questions or requests being asked

instances of inquiry or questions

No Comments

No Known Activations