INDEX

Explanations

titles or labels for related content

oai_token-act-pair · gpt-3.5-turbo

references to related stories and articles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gren

-0.66

 fructose

-0.63

-0.62

oshenko

-0.62

 randomly

-0.61

atron

-0.61

ASED

-0.60

 norm

-0.59

 unilaterally

-0.58

gran

-0.57

POSITIVE LOGITS

 Expand

0.91

 Cosponsors

0.80

 Learns

0.78

 Videos

0.78

 Legislation

0.75

 Articles

0.72

andise

0.71

ourses

0.71

anguage

0.69

 Reason

0.69

Activations Density 0.066%

titles or labels for related content

references to related stories and articles

No Comments

No Known Activations