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

Negative Logits

isu

-0.81

Reviewer

-0.76

ires

-0.76

ignty

-0.75

apons

-0.74

ubi

-0.74

ãĥ¯ãĥ³

-0.74

Sov

-0.74

Cra

-0.74

Si

-0.74

POSITIVE LOGITS

 harbor

0.69

ennett

0.68

 Reich

0.64

 cafeteria

0.64

 undocumented

0.64

 transcript

0.63

FDR

0.61

 Intercept

0.61

 Sussex

0.61

 Cornell

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.