INDEX

Explanations

positive descriptions or highlights

oai_token-act-pair · gpt-3.5-turbo

key events and highlights in narratives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hovah

-0.65

awa

-0.61

enegger

-0.56

onga

-0.53

 referen

-0.51

onto

-0.50

entimes

-0.49

 expires

-0.49

interstitial

-0.48

emale

-0.47

POSITIVE LOGITS

 yesterday

0.71

 Ples

0.54

 last

0.53

 Yanuk

0.53

 earlier

0.50

 Shields

0.50

 Priebus

0.47

 Thursday

0.45

 originally

0.44

 Arkham

0.44

Activations Density 2.047%

positive descriptions or highlights

key events and highlights in narratives

No Comments

No Known Activations