INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ´ãĤ¡

-0.79

":[

-0.76

Disc

-0.74

ãĥĩ

-0.72

 ILCS

-0.69

ovo

-0.69

çĦ

-0.69

":-

-0.67

extra

-0.66

Force

-0.66

POSITIVE LOGITS

 Rutherford

0.70

anooga

0.69

 Nash

0.69

 Lester

0.68

 ticking

0.65

 Boone

0.64

hof

0.64

inez

0.63

 Huntington

0.61

elines

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.