INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hostage

-0.70

resy

-0.68

pex

-0.66

 Sens

-0.64

dayName

-0.63

 sensing

-0.63

Commerce

-0.61

pard

-0.61

Press

-0.60

ampa

-0.60

POSITIVE LOGITS

hops

0.74

wered

0.70

ibaba

0.67

adders

0.64

idated

0.63

arette

0.63

 Mehran

0.62

 gulf

0.62

 unanim

0.61

adesh

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.