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

ucci

-0.72

 vanishing

-0.64

 comb

-0.63

iculture

-0.63

itud

-0.63

oters

-0.62

ios

-0.62

 externalToEVAOnly

-0.62

cells

-0.61

oter

-0.61

POSITIVE LOGITS

vich

0.72

Suc

0.68

 Akin

0.68

 Topic

0.67

bt

0.67

 âĶľâĶĢâĶĢ

0.66

gres

0.66

>]

0.66

md

0.65

gow

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.