INDEX

Explanations

objects or locations in a scene

oai_token-act-pair · gpt-3.5-turbo

specific nouns and concepts related to physical objects and subjects of discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Rated

-0.74

iliated

-0.64

 Interior

-0.55

Tur

-0.55

 Canad

-0.54

 Strip

-0.53

 Heat

-0.53

Pav

-0.53

 Capitalism

-0.52

STE

-0.52

POSITIVE LOGITS

 bandwagon

0.91

 fray

0.84

 ledge

0.78

iste

0.72

 ASAP

0.69

 whenever

0.68

ifice

0.65

 whilst

0.65

bench

0.65

 maker

0.64

Activations Density 0.660%

objects or locations in a scene

specific nouns and concepts related to physical objects and subjects of discussion

No Comments

No Known Activations