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

ãģ®éŃĶ

-0.82

 Newsp

-0.70

ateurs

-0.70

STER

-0.68

ayson

-0.67

ittee

-0.67

 sailors

-0.66

issance

-0.64

arella

-0.64

 Vintage

-0.64

POSITIVE LOGITS

assert

0.81

lvl

0.79

boards

0.70

function

0.69

pes

0.67

rahim

0.66

xual

0.65

sync

0.65

brid

0.65

facing

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.