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

 Pulitzer

-0.76

ulz

-0.71

ofi

-0.69

 seams

-0.68

senal

-0.68

 Lann

-0.66

pire

-0.66

qv

-0.65

icum

-0.65

 Keys

-0.64

POSITIVE LOGITS

gencies

0.86

riminal

0.76

ĪĴ

0.75

iannopoulos

0.72

éĹ

0.72

rompt

0.71

chuk

0.70

illery

0.70

ACTION

0.68

agogue

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.