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

thood

-0.76

 sleeper

-0.67

 redistributed

-0.67

 stranded

-0.67

rier

-0.66

bridge

-0.65

 smugglers

-0.64

 mapped

-0.63

rant

-0.63

inki

-0.62

POSITIVE LOGITS

ye

0.80

ãĥ¤

0.73

yz

0.68

herry

0.66

pell

0.64

0.63

ista

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.