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

Atl

-0.70

bour

-0.69

fb

-0.67

dn

-0.67

 Blues

-0.62

dj

-0.61

ffee

-0.61

gio

-0.61

nard

-0.61

rosso

-0.60

POSITIVE LOGITS

cyclopedia

0.65

 Standards

0.65

Aad

0.63

ortunately

0.63

 ende

0.62

swers

0.62

 discrim

0.60

 practition

0.60

 Excellence

0.60

 Hussein

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.