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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reloaded

-0.77

 Minotaur

-0.77

 Spear

-0.70

Cla

-0.67

 Metatron

-0.66

 Shogun

-0.62

 Babel

-0.62

 Reese

-0.62

 Tanzania

-0.62

 Ruler

-0.61

POSITIVE LOGITS

ours

0.76

gram

0.72

jobs

0.69

ad

0.67

uden

0.66

bish

0.66

achy

0.65

oly

0.65

 beaches

0.65

asu

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.