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

lling

-0.77

clusive

-0.71

dding

-0.71

atin

-0.68

culus

-0.68

erver

-0.67

lining

-0.67

cular

-0.65

 decomp

-0.65

ĪĴ

-0.64

POSITIVE LOGITS

});

0.73

=>

0.68

Saudi

0.67

borgh

0.65

 Cosponsors

0.64

 reperto

0.64

hide

0.63

à¹

0.62

kas

0.62

allo

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.