INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

OHN

-0.73

Scar

-0.70

adish

-0.69

review

-0.65

-0.61

 mull

-0.61

absor

-0.59

tips

-0.59

Variable

-0.59

nuts

-0.59

POSITIVE LOGITS

itions

0.77

 Â¶

0.76

merce

0.74

vironment

0.72

andowski

0.71

omb

0.67

croft

0.66

nel

0.64

 hemisphere

0.64

gger

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.