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

eny

-0.74

 spot

-0.72

ounter

-0.70

ovie

-0.67

ldom

-0.65

ensen

-0.64

aimon

-0.63

ounters

-0.62

etz

-0.62

chwitz

-0.62

POSITIVE LOGITS

soever

0.70

Ago

0.68

Shape

0.68

 Catalan

0.67

awa

0.66

 Westminster

0.66

ãĤ±

0.65

 Governments

0.65

 sovere

0.63

 Canaver

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.