INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ogle

-0.81

plet

-0.81

agos

-0.75

clair

-0.75

ilic

-0.74

autical

-0.73

ilk

-0.73

olla

-0.71

vernment

-0.71

enza

-0.71

POSITIVE LOGITS

 Result

0.70

Obj

0.68

GEN

0.63

NEC

0.62

fitted

0.61

++++++++++++++++

0.61

å§

0.61

 reflections

0.60

ãĥŃ

0.60

ogether

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.