INDEX

Explanations

the word "mixed" with varying degrees of intensity

oai_token-act-pair · gpt-3.5-turbo

references to 'mixed' as a descriptor for various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

dfx

-0.91

onds

-0.76

ond

-0.73

ocene

-0.70

debian

-0.66

ury

-0.65

inders

-0.64

 Annotations

-0.64

arers

-0.63

onding

-0.62

POSITIVE LOGITS

 sexes

0.78

iple

0.75

 martial

0.75

 feelings

0.74

 mixed

0.72

 mixes

0.67

 genders

0.66

 Mixed

0.65

mix

0.64

 mixing

0.62

Activations Density 0.018%

the word "mixed" with varying degrees of intensity

references to 'mixed' as a descriptor for various subjects

No Comments

No Known Activations