INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 disapproval

-0.77

 resistance

-0.72

 uphill

-0.69

 nuns

-0.67

 directions

-0.66

 hearts

-0.65

 objections

-0.64

RS

-0.64

 disobedience

-0.63

 campuses

-0.62

POSITIVE LOGITS

Pwr

0.72

angible

0.72

 Tradable

0.71

£ı

0.69

Tool

0.69

eme

0.69

 Portable

0.69

 Mortgage

0.67

VERTIS

0.67

mt

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.