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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Painter

-0.67

affer

-0.66

lich

-0.62

Bang

-0.62

 lich

-0.62

 drowning

-0.61

 skipping

-0.59

 Gamer

-0.59

Ash

-0.59

isconsin

-0.58

POSITIVE LOGITS

etsk

0.87

culosis

0.86

kefeller

0.86

esis

0.76

pert

0.76

 Kepler

0.73

 Sovere

0.72

sonian

0.72

tsky

0.71

ventus

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.