INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

olson

-0.72

cade

-0.70

resent

-0.67

 rall

-0.66

 beaut

-0.66

 Raider

-0.66

yles

-0.65

matter

-0.64

iage

-0.63

 flares

-0.63

POSITIVE LOGITS

assian

0.69

ĨĴ

0.69

atche

0.68

Tier

0.63

 Clause

0.63

itative

0.62

 Catholicism

0.61

 Cosponsors

0.61

uania

0.60

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.