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

orp

-0.73

phabet

-0.68

byss

-0.65

iffe

-0.65

atin

-0.63

iving

-0.62

ials

-0.62

arcity

-0.61

arna

-0.61

orate

-0.61

POSITIVE LOGITS

Installation

0.70

 guid

0.69

Sensor

0.68

[[

0.67

sov

0.65

Pry

0.65

oyle

0.61

Textures

0.60

emi

0.59

 Inventory

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.