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

phys

-0.74

roc

-0.69

ouls

-0.67

adelphia

-0.66

ktop

-0.66

arij

-0.66

payers

-0.66

raf

-0.64

ramid

-0.63

library

-0.63

POSITIVE LOGITS

ãĥ³ãĤ¸

0.74

å§«

0.72

ãĥ¤

0.69

å¥³

0.68

ãĥĬ

0.66

²¾

0.62

ãĤ¬

0.61

 depths

0.60

 Chaser

0.60

ttle

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.