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

 conform

-0.78

ional

-0.72

ract

-0.71

icism

-0.68

hammad

-0.68

gary

-0.66

ion

-0.64

eous

-0.64

lies

-0.64

obal

-0.63

POSITIVE LOGITS

é¾įåĸļå£«

0.83

Lear

0.72

Wallet

0.71

senal

0.71

Gaza

0.68

Jen

0.68

Jew

0.67

 Genie

0.66

 Explorer

0.66

 Kinder

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.