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

èĢħ

-0.82

UA

-0.75

quest

-0.65

åĤ

-0.65

 Stretch

-0.64

Pod

-0.63

 Publishers

-0.62

UTION

-0.60

<+

-0.60

humans

-0.60

POSITIVE LOGITS

 Cabrera

0.78

abase

0.68

odge

0.66

 extras

0.66

oret

0.64

Wyn

0.63

wise

0.62

reau

0.60

 traveller

0.60

 ashore

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.