INDEX

Explanations

proper nouns related to notable or well-known individuals, places, or organizations

oai_token-act-pair · gpt-3.5-turbo

references to significant individuals and events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.68

*/(

-0.61

rawdownloadcloneembedreportprint

-0.56

 cautiously

-0.55

 councillors

-0.55

 strategically

-0.54

quickShipAvailable

-0.53

BILITIES

-0.53

lations

-0.52

eric

-0.51

POSITIVE LOGITS

oslov

0.54

ago

0.53

"),

0.48

 Soviet

0.47

"],

0.47

 Brothers

0.45

 Yugoslavia

0.44

 nightclub

0.44

").

0.43

å£«

0.43

Activations Density 1.012%

proper nouns related to notable or well-known individuals, places, or organizations

references to significant individuals and events

No Comments

No Known Activations