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

zens

-0.73

otti

-0.73

arkin

-0.72

ombies

-0.67

 onion

-0.66

tesy

-0.62

edition

-0.62

igraph

-0.60

eta

-0.58

microsoft

-0.58

POSITIVE LOGITS

GBT

0.80

.}

0.77

OUN

0.66

ãĤ¡

0.66

%%

0.65

?:

0.65

 hesitation

0.62

achelor

0.61

jri

0.58

Fight

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.