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

rine

-0.73

ataka

-0.68

Shape

-0.67

rawdownloadcloneembedreportprint

-0.66

ogan

-0.66

yne

-0.66

 amuse

-0.65

 chatter

-0.65

odon

-0.64

Rog

-0.63

POSITIVE LOGITS

pressed

0.71

 Extrem

0.70

 Associ

0.68

LIA

0.68

itton

0.68

 VERS

0.68

 Vietnamese

0.66

liter

0.64

 Canaan

0.62

stra

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.