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

hess

-0.78

unic

-0.77

unal

-0.77

steen

-0.76

agall

-0.73

quest

-0.70

alde

-0.69

imaru

-0.68

nation

-0.68

sted

-0.66

POSITIVE LOGITS

 DRAG

0.76

 Riding

0.75

 Defenders

0.73

 subsistence

0.69

orthy

0.66

Gat

0.65

 COUR

0.65

 Braz

0.64

arching

0.64

awa

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.