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

igating

-0.69

estation

-0.69

 compuls

-0.68

 jaws

-0.67

isition

-0.67

esting

-0.66

aganda

-0.65

ibling

-0.64

asms

-0.63

acing

-0.63

POSITIVE LOGITS

MAL

0.66

USER

0.65

POL

0.65

MAG

0.64

åĪ

0.63

HRC

0.63

atel

0.63

Cu

0.63

nai

0.62

ACY

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.