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

TABLE

-0.75

Scroll

-0.71

RIC

-0.70

 VIDEOS

-0.69

pecially

-0.68

ref

-0.68

":"/

-0.67

ä¹ĭ

-0.65

 Drops

-0.64

imeter

-0.63

POSITIVE LOGITS

jad

0.77

 unpop

0.73

 Adin

0.73

 arson

0.67

 Faust

0.66

minded

0.66

 Falk

0.66

 Lilith

0.65

 corrid

0.63

 Werewolf

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.