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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SEA

-0.85

CHAT

-0.70

KY

-0.67

pak

-0.67

Fuel

-0.65

Loading

-0.63

OSH

-0.62

KE

-0.61

Orig

-0.61

pee

-0.60

POSITIVE LOGITS

vati

0.83

theless

0.75

 guiName

0.71

ebted

0.67

 Williamson

0.67

enburg

0.67

Alz

0.66

 deprecated

0.66

ÅĤ

0.65

Alc

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.