INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

iP

-0.90

Motor

-0.79

 Picks

-0.75

Market

-0.73

Cash

-0.72

Dear

-0.71

Tam

-0.70

DAQ

-0.70

Hon

-0.69

Sharp

-0.69

POSITIVE LOGITS

ĺħ

0.85

 commun

0.70

ĨĴ

0.69

blance

0.67

 resid

0.65

fun

0.65

 algebra

0.64

Ĥİ

0.63

 twentieth

0.63

olate

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.