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

atever

-0.67

itiveness

-0.64

¿½

-0.64

oenix

-0.61

bud

-0.61

baum

-0.60

 hybrid

-0.59

 soaking

-0.59

amber

-0.59

orient

-0.56

POSITIVE LOGITS

quez

0.75

daq

0.72

EStreamFrame

0.70

 externalToEVAOnly

0.69

 Franch

0.68

RAW

0.66

 DEFENSE

0.66

 Decay

0.65

 Voters

0.64

 guiName

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.