INDEX

Explanations

instances where the phrase "could not" appears

oai_token-act-pair · gpt-3.5-turbo

negation phrases and forms of the verb "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

artifacts

-0.74

hyde

-0.72

interstitial

-0.72

amous

-0.70

soDeliveryDate

-0.70

govtrack

-0.65

 Notting

-0.63

cases

-0.62

entin

-0.61

notation

-0.60

POSITIVE LOGITS

 foresee

0.89

 afford

0.84

athom

0.78

 conce

0.75

 feas

0.73

 imagine

0.73

 cope

0.72

 conceive

0.71

 parse

0.70

 discern

0.68

Activations Density 0.124%

instances where the phrase "could not" appears

negation phrases and forms of the verb "to be."

No Comments

No Known Activations