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

ansk

-0.68

othal

-0.68

ourcing

-0.68

prison

-0.65

abulary

-0.65

igation

-0.65

wagen

-0.64

encing

-0.63

ploma

-0.62

onding

-0.62

POSITIVE LOGITS

Ka

0.77

 Valiant

0.63

acted

0.63

 contrasts

0.63

 Savage

0.62

ached

0.61

VK

0.61

Taj

0.61

anna

0.61

ModLoader

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.