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

è¯

-0.83

orsche

-0.80

onne

-0.77

asive

-0.73

Dialog

-0.70

NRS

-0.68

ibling

-0.68

-0.67

eway

-0.67

Cas

-0.66

POSITIVE LOGITS

luster

0.72

vac

0.66

tainment

0.64

 toppled

0.64

Í

0.63

 clocks

0.62

 Patriot

0.62

 ousted

0.62

 liberating

0.61

 frig

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.