INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ensation

-0.72

mble

-0.68

itarian

-0.66

 visas

-0.66

yright

-0.65

 Neptune

-0.64

jet

-0.63

 planet

-0.62

 temper

-0.62

 pedal

-0.61

POSITIVE LOGITS

Reloaded

0.87

 Mayhem

0.79

 Reloaded

0.76

Coy

0.71

ÃįÃį

0.69

 unanswered

0.68

aughtered

0.68

0.67

Interstitial

0.67

ĪĴ

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.