INDEX

Explanations

phrases expressing uncertainty or confusion about what to do in a situation

oai_token-act-pair · gpt-3.5-turbo

phrases that express confusion or uncertainty about actions and events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liam

-0.72

uably

-0.66

ramid

-0.64

 advocates

-0.63

 controversies

-0.62

eatures

-0.61

 advoc

-0.60

 endors

-0.59

iosyncr

-0.59

 Lifetime

-0.58

POSITIVE LOGITS

 beforehand

1.05

 anymore

0.97

0.89

 downstairs

0.88

 upstairs

0.87

.;

0.87

!.

0.86

.[

0.83

++;

0.83

ãĢĤ

0.83

Activations Density 0.706%

phrases expressing uncertainty or confusion about what to do in a situation

phrases that express confusion or uncertainty about actions and events

No Comments

No Known Activations