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

ITH

-0.68

ITE

-0.67

+)

-0.67

 poss

-0.67

zu

-0.61

IVERS

-0.61

 VERS

-0.61

BUS

-0.61

CLOSE

-0.60

EX

-0.59

POSITIVE LOGITS

meier

0.78

 Mead

0.71

 Masonic

0.70

 Lutheran

0.68

 Gutenberg

0.67

hoe

0.66

ieri

0.65

agne

0.63

arine

0.63

 McKenna

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.