INDEX

Explanations

phrases indicating uncertainty or speculative statements

oai_token-act-pair · gpt-3.5-turbo

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

former

-0.61

ouf

-0.60

noon

-0.57

quartered

-0.56

AAA

-0.55

kie

-0.55

 Saying

-0.54

 Coffin

-0.52

 Trouble

-0.52

POSITIVE LOGITS

beh

1.50

 seems

1.30

 becomes

1.24

 begs

1.23

 appears

1.16

 shouldn

1.13

 makes

1.06

 feels

1.04

unes

1.04

 hurts

1.03

Activations Density 0.150%

phrases indicating uncertainty or speculative statements

No Comments

No Known Activations