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

spection

-0.72

 Diss

-0.71

ASED

-0.67

IPM

-0.62

 Hels

-0.62

 Dish

-0.62

RD

-0.61

 Lans

-0.61

assisted

-0.61

glas

-0.61

POSITIVE LOGITS

ippery

0.84

autical

0.75

ictionary

0.73

ernels

0.73

abulary

0.72

alysis

0.71

umat

0.71

orsche

0.69

ippi

0.69

eca

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.