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

grave

-0.79

etsy

-0.75

ravel

-0.74

akings

-0.73

enery

-0.69

IOR

-0.68

ridges

-0.68

nery

-0.67

iet

-0.67

route

-0.67

POSITIVE LOGITS

inav

0.75

partisan

0.73

racial

0.68

 Lanka

0.66

ublic

0.65

econom

0.65

 chrom

0.65

 economics

0.64

 markets

0.60

 socialism

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.