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

weet

-0.72

beans

-0.70

ohan

-0.69

istine

-0.67

ogle

-0.67

enged

-0.64

opus

-0.63

wolves

-0.63

nis

-0.63

pha

-0.63

POSITIVE LOGITS

 webcam

0.73

 thrott

0.70

 srfAttach

0.65

 princ

0.64

 Cosmetic

0.63

SSD

0.62

Tie

0.60

srf

0.59

 Writer

0.59

 scanners

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.