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

ils

-0.81

enced

-0.75

ital

-0.75

upp

-0.74

isco

-0.73

eport

-0.72

ution

-0.70

isites

-0.68

ence

-0.68

lav

-0.67

POSITIVE LOGITS

 Gamble

0.69

Phi

0.62

Num

0.58

 counted

0.58

 bruising

0.57

rogens

0.57

 Slayer

0.56

 Heidi

0.56

Newsletter

0.56

 bott

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.