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

ãĤ¢

-0.74

eton

-0.68

ãģĨ

-0.67

åĳ

-0.67

Zup

-0.67

 Helpful

-0.65

 Accuracy

-0.63

ãģı

-0.62

ERY

-0.62

 rapp

-0.61

POSITIVE LOGITS

olla

0.70

killer

0.65

anol

0.62

aster

0.60

killers

0.60

 sperm

0.60

wagen

0.59

 suspensions

0.58

act

0.58

inals

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.