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

elsen

-0.72

 captcha

-0.71

 inexperienced

-0.67

 accountant

-0.66

ourke

-0.66

 commissioner

-0.65

 guiActiveUn

-0.65

erial

-0.65

 assistants

-0.63

 commissions

-0.63

POSITIVE LOGITS

 Treatment

0.83

hement

0.79

 Therapy

0.74

tion

0.73

Dialogue

0.72

tl

0.70

Reloaded

0.68

 Remastered

0.67

 Genocide

0.66

rencies

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.