INDEX

Explanations

phrases indicating an action that happens before a specific event or outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate actions or events occurring prior to something else

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hack

-0.82

Writer

-0.69

olog

-0.67

DC

-0.67

aez

-0.66

oret

-0.66

Die

-0.65

PROV

-0.65

amount

-0.64

NRS

-0.64

POSITIVE LOGITS

 sunset

0.79

 committing

0.74

 embark

0.72

 sunrise

0.71

 midnight

0.70

 serving

0.69

 realizing

0.69

 Thumbnails

0.67

 noon

0.66

 supper

0.66

Activations Density 0.062%

phrases indicating an action that happens before a specific event or outcome

phrases that indicate actions or events occurring prior to something else

No Comments

No Known Activations