INDEX

Explanations

references to particular sections in a text structure

oai_token-act-pair · gpt-3.5-turbo

references to ongoing stories or narratives in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

»Ĵ

-0.74

ŃĶ

-0.63

 fame

-0.62

ibilities

-0.61

«ĺ

-0.60

 abstinence

-0.59

eco

-0.58

Ĥ¬

-0.57

uits

-0.57

DEM

-0.56

POSITIVE LOGITS

 Continued

0.86

tenance

0.77

 caption

0.71

hart

0.70

telling

0.68

 Trend

0.63

"></

0.62

advertisement

0.62

biz

0.62

line

0.62

Activations Density 0.008%

references to particular sections in a text structure

references to ongoing stories or narratives in a document

No Comments

No Known Activations