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

 agre

-0.80

 DRAG

-0.77

ãĤ©

-0.74

 tradem

-0.72

aturdays

-0.71

çĶ°

-0.71

 surname

-0.70

 patience

-0.69

 unborn

-0.68

 inexper

-0.67

POSITIVE LOGITS

artz

0.77

RAW

0.69

ackers

0.68

Container

0.64

Ans

0.64

Story

0.64

Wiz

0.62

 Anonymous

0.62

cci

0.60

aters

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.