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

 Bers

-0.75

isks

-0.74

ĻĤ

-0.74

ĺħ

-0.73

pires

-0.73

ogle

-0.69

cart

-0.67

ORPG

-0.67

raid

-0.67

antis

-0.66

POSITIVE LOGITS

auna

0.73

AST

0.73

@@

0.72

 avail

0.71

heed

0.69

Geo

0.67

uti

0.67

 witnesses

0.67

 revel

0.65

 rejo

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.