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

rolet

-0.77

 remotely

-0.65

laden

-0.65

 yourselves

-0.63

HQ

-0.63

ahi

-0.63

 Tuls

-0.63

BYU

-0.63

nesota

-0.62

icial

-0.61

POSITIVE LOGITS

 waning

0.68

glers

0.68

ffe

0.62

 Princ

0.61

 Straw

0.61

)</

0.61

 Bowser

0.61

 Punk

0.61

 Tags

0.60

 Niet

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.