INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

¹

-0.79

rower

-0.74

iosis

-0.73

¶ħ

-0.72

edd

-0.71

riz

-0.69

hood

-0.69

ris

-0.69

face

-0.67

imester

-0.65

POSITIVE LOGITS

 nostalg

0.72

oyal

0.70

 ingred

0.68

 therap

0.64

ashtra

0.63

 separatist

0.63

 oppress

0.63

Planet

0.63

Marx

0.63

 Conservation

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.