INDEX

Explanations

locations in news articles

oai_token-act-pair · gpt-3.5-turbo

the word "in" and its occurrences within contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.76

Firstly

-0.68

»Ĵ

-0.64

 rapists

-0.64

few

-0.62

wolves

-0.62

 absorbs

-0.62

Ĥİ

-0.60

->

-0.60

killers

-0.60

POSITIVE LOGITS

 downtown

0.95

 front

0.92

window

0.91

adena

0.87

 foreground

0.86

 conjunction

0.85

 commem

0.84

 celebration

0.82

 southeastern

0.82

 Havana

0.80

Activations Density 0.089%

locations in news articles

the word "in" and its occurrences within contexts

No Comments

No Known Activations