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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dressing

-0.66

 attendant

-0.66

meal

-0.65

 garn

-0.65

 offic

-0.63

aged

-0.63

 submar

-0.62

uman

-0.61

 presided

-0.60

 watering

-0.60

POSITIVE LOGITS

romy

0.72

igue

0.68

ensional

0.67

illon

0.66

urtles

0.66

 Vive

0.66

Ã¨re

0.65

multiple

0.63

çĭ

0.63

é¾įåĸļå£«

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.