INDEX

Explanations

locations or events mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

occurrences of locations and associated events

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

channelAvailability

-0.72

BILITIES

-0.70

âĿ

-0.69

catentry

-0.67

Entity

-0.66

 pirates

-0.65

saf

-0.65

 experimented

-0.65

 rapists

-0.65

%%

-0.64

POSITIVE LOGITS

 Cannes

0.95

 conjunction

0.92

 June

0.91

 February

0.88

 commem

0.88

 Sochi

0.88

 March

0.87

 Newport

0.86

 Venice

0.84

 April

0.84

Activations Density 0.229%

locations or events mentioned in news articles

occurrences of locations and associated events

No Comments

No Known Activations