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

pload

-0.72

 missed

-0.64

 buzzing

-0.63

axies

-0.63

 neigh

-0.63

 shed

-0.63

ãĥ£

-0.63

 tyres

-0.63

 bang

-0.62

rimp

-0.62

POSITIVE LOGITS

ieth

0.74

lik

0.72

threatening

0.70

 Amon

0.68

ulative

0.68

 Practice

0.68

IDA

0.67

DOS

0.66

lis

0.65

RH

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.