INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 compost

-0.80

 coffers

-0.72

 proport

-0.71

 sacrific

-0.71

 periphery

-0.69

 obligatory

-0.67

 recorder

-0.66

 clutter

-0.66

 reps

-0.66

 coma

-0.66

POSITIVE LOGITS

lee

1.41

URI

0.77

olean

0.73

owl

0.70

Vari

0.68

 Wyatt

0.68

ces

0.67

cest

0.67

åĨ

0.64

Electric

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.