INDEX

Explanations

mentions of skepticism or doubt

oai_token-act-pair · gpt-3.5-turbo

words that indicate doubt or skepticism regarding claims or assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

acus

-0.87

adan

-0.87

uits

-0.86

achev

-0.84

ften

-0.84

utics

-0.82

ateurs

-0.80

vet

-0.78

ascript

-0.78

arden

-0.77

POSITIVE LOGITS

 occurrence

0.89

 prevalence

0.87

 incidence

0.86

 global

0.81

 number

0.81

 lack

0.81

 objective

0.80

 inability

0.79

 tendency

0.78

 substance

0.78

Activations Density 0.126%

mentions of skepticism or doubt

words that indicate doubt or skepticism regarding claims or assertions

No Comments

No Known Activations