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

"?

-0.69

 Card

-0.63

oster

-0.63

rast

-0.62

Card

-0.61

ox

-0.61

arov

-0.60

 spaced

-0.60

apers

-0.59

apes

-0.59

POSITIVE LOGITS

toe

0.72

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.72

 à¨

0.70

 rooting

0.68

ashtra

0.68

mary

0.67

ÂłÂłÂł

0.67

ÂłÂłÂłÂł

0.66

 Imper

0.66

staking

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.