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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sidx

-0.69

ibaba

-0.66

 salty

-0.65

agara

-0.62

 favorable

-0.61

ategory

-0.60

pie

-0.59

ideshow

-0.59

 fatally

-0.59

venue

-0.58

POSITIVE LOGITS

auri

0.75

sett

0.73

immer

0.71

ĳå£«

0.69

ulum

0.68

enez

0.67

alore

0.67

¬

0.67

management

0.66

 Journals

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.