INDEX

Explanations

references to professionals and their treatment or characteristics in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to professionals in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

apo

-0.75

 Territories

-0.68

 Railroad

-0.65

seed

-0.63

DeL

-0.62

 Meier

-0.62

forth

-0.62

 Amos

-0.62

 Boat

-0.61

FACE

-0.61

POSITIVE LOGITS

umers

0.93

 professionals

0.88

 specialize

0.86

ically

0.86

paces

0.84

 specializing

0.84

olicy

0.82

icians

0.80

assetsadobe

0.80

linger

0.80

Activations Density 0.010%

references to professionals and their treatment or characteristics in various contexts

references to professionals in various fields

No Comments

No Known Activations