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

ews

-0.81

cs

-0.80

elines

-0.77

ings

-0.76

ographs

-0.75

wives

-0.74

ntil

-0.72

alias

-0.71

ologies

-0.71

zes

-0.70

POSITIVE LOGITS

 Archdemon

0.85

Higher

0.74

TEXTURE

0.69

DPR

0.69

unda

0.69

 dissatisf

0.67

KEN

0.65

 Eighth

0.65

Ard

0.65

CBD

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.