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

andel

-0.80

lation

-0.80

activation

-0.78

perse

-0.76

ppe

-0.76

essen

-0.74

je

-0.73

omorph

-0.71

angled

-0.70

schild

-0.70

POSITIVE LOGITS

 removable

0.84

 Vanity

0.69

NX

0.68

 Torch

0.67

 Outs

0.66

Vul

0.64

Umb

0.64

Characters

0.64

 Barrett

0.63

 playable

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.