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

Negative Logits

 Pract

-0.65

 Murray

-0.64

 Scheme

-0.63

 Swanson

-0.62

effic

-0.62

 Tennis

-0.62

Users

-0.61

 Wass

-0.60

apple

-0.60

 Brewer

-0.60

POSITIVE LOGITS

yip

0.93

iful

0.77

 sleeper

0.69

eele

0.69

 prest

0.67

 lockdown

0.65

atform

0.64

:]

0.63

dial

0.63

 pillars

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.