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

Reference

-0.86

aptic

-0.73

..................

-0.72

lie

-0.70

âĶĢâĶĢ

-0.68

 Chapters

-0.67

 Nurse

-0.67

................................

-0.66

........................

-0.65

IDE

-0.65

POSITIVE LOGITS

chell

0.70

gur

0.69

 specials

0.65

photos

0.64

olulu

0.64

grounds

0.63

pse

0.62

orno

0.60

 shots

0.60

duction

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.