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

 unden

-0.86

ares

-0.81

erm

-0.75

dimension

-0.72

Bridge

-0.72

erb

-0.70

jab

-0.69

yp

-0.68

rar

-0.68

 challeng

-0.67

POSITIVE LOGITS

sect

0.64

 survived

0.64

 ital

0.63

 update

0.62

 embedded

0.60

 cured

0.60

geist

0.60

 regress

0.59

 Courier

0.58

GIF

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.