INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

omething

-0.74

bol

-0.70

 parentheses

-0.67

umatic

-0.67

*/(

-0.65

 Scotia

-0.63

nered

-0.63

atos

-0.63

hon

-0.63

 Huss

-0.63

POSITIVE LOGITS

********************************

0.75

si

0.74

duino

0.72

Ver

0.71

SEE

0.69

 Flint

0.66

READ

0.66

Null

0.66

JJ

0.64

Initialized

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.