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

tnc

-0.81

atars

-0.68

hattan

-0.65

yond

-0.64

idays

-0.62

planes

-0.61

tumblr

-0.61

ourgeois

-0.61

hatt

-0.60

WF

-0.59

POSITIVE LOGITS

ked

0.82

avia

0.72

enced

0.69

imer

0.67

osures

0.66

uclear

0.66

auna

0.66

anus

0.65

ovie

0.64

ãĥĸ

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.