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

Negative Logits

 Finder

-0.67

tein

-0.64

ucket

-0.64

poral

-0.61

 Plot

-0.60

uber

-0.59

 reinstated

-0.59

atcher

-0.59

 Extensions

-0.59

mbuds

-0.58

POSITIVE LOGITS

hya

0.66

rums

0.65

ochemistry

0.64

phabet

0.63

Meta

0.62

 LORD

0.61

 shenan

0.61

Reviewer

0.61

ocene

0.61

 gimm

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.