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

assed

-0.67

md

-0.67

pez

-0.64

tmp

-0.63

 Century

-0.63

adr

-0.62

ibrary

-0.62

ende

-0.62

atem

-0.61

pb

-0.60

POSITIVE LOGITS

lihood

0.74

zik

0.72

lam

0.66

iations

0.66

ptions

0.64

lations

0.63

angelo

0.63

Wallet

0.61

nings

0.60

Chart

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.