INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

uin

-0.92

ãĥ´

-0.80

Ther

-0.73

inav

-0.72

arbon

-0.71

thur

-0.71

Liquid

-0.70

Union

-0.69

ilk

-0.69

KB

-0.67

POSITIVE LOGITS

 assignments

0.75

aukee

0.74

 Rollins

0.70

 cutoff

0.69

 chores

0.68

 assigning

0.67

 favoring

0.66

roid

0.66

 stacking

0.66

ansky

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.