INDEX

Explanations

dates and locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

dates and relevant events in a timeline format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 haun

-0.62

unia

-0.53

 ................

-0.53

ukes

-0.52

dule

-0.52

xxxx

-0.51

hops

-0.48

 curls

-0.48

 Arnold

-0.48

omas

-0.47

POSITIVE LOGITS

*/(

0.58

)—

0.57

axy

0.56

)--

0.54

arbon

0.54

avier

0.54

Reuters

0.53

verning

0.53

entin

0.53

âĶĢ

0.52

Activations Density 0.097%

dates and locations mentioned in news articles

dates and relevant events in a timeline format

No Comments

No Known Activations