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

rals

-0.77

olved

-0.73

cott

-0.73

ierrez

-0.73

 divest

-0.72

elling

-0.69

ihil

-0.69

 disarm

-0.69

irtual

-0.68

 recogn

-0.67

POSITIVE LOGITS

hua

0.67

hots

0.66

boot

0.65

 Rosenstein

0.64

 AUTH

0.63

astern

0.63

 Ended

0.63

channelAvailability

0.60

Enlarge

0.60

 Needless

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.