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

 Born

-0.71

*/(

-0.67

Flying

-0.66

 lobb

-0.65

Reward

-0.64

 Municip

-0.64

 sidx

-0.62

 Amen

-0.62

 helpers

-0.62

nesota

-0.62

POSITIVE LOGITS

wine

0.80

arted

0.75

gio

0.72

bery

0.72

terness

0.70

acc

0.70

ols

0.70

WB

0.70

BP

0.70

iban

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.