INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

inguishable

-0.76

 stumbling

-0.74

 exchange

-0.69

 collapsing

-0.69

interstitial

-0.67

 demanding

-0.66

 signalling

-0.64

 recognised

-0.62

 yield

-0.61

 unavoidable

-0.60

POSITIVE LOGITS

pmwiki

0.75

dayName

0.70

NSA

0.68

Nin

0.67

 Satanic

0.65

————

0.64

oles

0.63

grade

0.62

ORTS

0.62

 Misc

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.