INDEX

Explanations

phrases indicating uncertainty about potential actions or outcomes

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating possibility or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 earthqu

-0.75

ThumbnailImage

-0.67

Þ

-0.66

isSpecial

-0.65

 referen

-0.65

cloneembedreportprint

-0.63

 Polic

-0.60

eye

-0.58

 externalTo

-0.57

ò

-0.57

POSITIVE LOGITS

Not

0.88

't

0.85

not

0.83

not

0.80

Not

0.76

abouts

0.75

BE

0.71

NOT

0.70

NOT

0.69

ode

0.68

Activations Density 0.051%

phrases indicating uncertainty about potential actions or outcomes

modal verbs indicating possibility or uncertainty

No Comments

No Known Activations