INDEX

Explanations

instances of uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possibility or uncertainty

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

osi

-0.69

anding

-0.60

 Crown

-0.60

wait

-0.60

anwhile

-0.59

atin

-0.58

dding

-0.57

POS

-0.57

 plaintiff

-0.56

 Burning

-0.55

POSITIVE LOGITS

 been

1.28

 gotten

1.26

been

1.12

gotten

1.06

 gone

1.05

 Been

0.98

 undergone

0.97

 arisen

0.92

 begun

0.91

 taken

0.91

Activations Density 0.095%

instances of uncertainty or speculation

phrases indicating possibility or uncertainty

No Comments

No Known Activations