INDEX

Explanations

phrases indicating possibility or speculation

oai_token-act-pair · gpt-3.5-turbo

phrases that express possibility or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Blaze

-0.74

 Powered

-0.66

 Roose

-0.66

 stalking

-0.65

 Slug

-0.64

ULTS

-0.62

Cho

-0.62

Us

-0.61

 Mour

-0.61

bum

-0.61

POSITIVE LOGITS

 speculate

1.45

 presume

1.21

't

1.20

 conclude

1.20

 infer

1.18

 imagine

1.18

 argue

1.17

 assume

1.14

 safely

1.13

 hypothes

1.09

Activations Density 0.076%

phrases indicating possibility or speculation

phrases that express possibility or capability

No Comments

No Known Activations