INDEX

Explanations

phrases related to accountability and responsibility

oai_token-act-pair · gpt-3.5-turbo

references to accountability and responsibility

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

 Finish

-0.75

naire

-0.65

clus

-0.63

levard

-0.62

Finish

-0.61

 Explorer

-0.60

 Advance

-0.60

 Move

-0.58

hunter

-0.58

imal

-0.58

POSITIVE LOGITS

 accountable

1.72

 hostage

1.40

 ransom

1.26

 responsible

1.07

 captive

1.00

responsible

1.00

 liable

0.99

account

0.86

 culp

0.85

 criminally

0.85

Activations Density 0.146%

phrases related to accountability and responsibility

references to accountability and responsibility

No Comments

No Known Activations