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

anian

-0.88

amily

-0.73

SPONSORED

-0.70

ioned

-0.70

armed

-0.69

 suspic

-0.65

cient

-0.64

 Clause

-0.61

room

-0.61

eyed

-0.60

POSITIVE LOGITS

\\\\\\\\

0.78

Ì¶

0.69

 Canaveral

0.67

voy

0.67

Ocean

0.66

GY

0.66

NAS

0.65

jri

0.65

inar

0.65

ãĤ¦

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.