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

NK

-0.80

ï¸

-0.74

 resemb

-0.73

irlf

-0.73

[|

-0.72

RIS

-0.68

NRS

-0.67

GSL

-0.67

MMR

-0.67

å¦

-0.66

POSITIVE LOGITS

uddin

0.69

builder

0.65

opathy

0.65

ajo

0.64

vent

0.64

agate

0.63

stic

0.63

building

0.62

 charter

0.62

builders

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.