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

kees

-0.78

CLASSIFIED

-0.74

fair

-0.73

KS

-0.69

sup

-0.65

angs

-0.65

ives

-0.64

inqu

-0.63

adr

-0.63

fred

-0.62

POSITIVE LOGITS

inburgh

0.79

 performer

0.69

ourney

0.69

NCT

0.68

 stained

0.66

rison

0.65

 rehearsal

0.63

 plumbing

0.63

Op

0.62

hyde

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.