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

din

-0.74

anus

-0.73

umar

-0.67

terness

-0.67

imar

-0.67

idia

-0.67

ataka

-0.65

erson

-0.64

istries

-0.64

iversal

-0.63

POSITIVE LOGITS

arity

0.69

 Yards

0.68

RFC

0.66

OTOS

0.65

ZI

0.63

grab

0.62

ktop

0.62

éĹ

0.61

OSS

0.60

HQ

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.