INDEX

Explanations

highlights and key points in news stories

oai_token-act-pair · gpt-3.5-turbo

sections that summarize key points or highlights from stories or 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

 nurs

-0.85

unci

-0.79

ogly

-0.78

ŃĶ

-0.75

tails

-0.72

abase

-0.70

olesc

-0.68

ander

-0.67

unt

-0.67

andro

-0.67

POSITIVE LOGITS

 WATCHED

0.80

ï

0.75

 Surveillance

0.73

 Researchers

0.72

 Decoder

0.71

 Highlights

0.71

 Kaine

0.71

 Transcript

0.70

 Videos

0.70

 Legislation

0.69

Activations Density 0.016%

highlights and key points in news stories

sections that summarize key points or highlights from stories or articles

No Comments

No Known Activations