INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 sidx

-0.79

ONY

-0.69

sov

-0.69

 Synd

-0.66

 Petro

-0.65

 Yugoslav

-0.63

 Lomb

-0.62

inces

-0.61

elligence

-0.60

DPR

-0.60

POSITIVE LOGITS

bourg

0.84

Discussion

0.71

ocrin

0.70

guards

0.68

earch

0.67

ibrary

0.67

butt

0.65

cdn

0.64

 verification

0.64

upload

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.