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

 enthus

-0.68

idding

-0.67

 mortality

-0.64

metics

-0.64

 likeness

-0.63

 sarc

-0.61

 artific

-0.60

 burial

-0.60

 conversion

-0.59

¢

-0.59

POSITIVE LOGITS

ounces

0.72

CDC

0.70

HP

0.70

hari

0.69

enger

0.69

aired

0.68

MS

0.68

 Ride

0.65

HF

0.65

SOURCE

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.