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

Vul

-0.69

icz

-0.68

txt

-0.67

inth

-0.67

Ãº

-0.67

 stub

-0.65

ublic

-0.65

ript

-0.65

lete

-0.64

XXX

-0.63

POSITIVE LOGITS

 Cosponsors

0.79

 artif

0.77

athy

0.77

 energy

0.71

itely

0.68

 Heller

0.67

Ther

0.67

Energy

0.67

atra

0.65

hyde

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.