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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Magikarp

-0.77

ertodd

-0.70

 warr

-0.69

ãģ®éŃĶ

-0.68

 Missions

-0.65

 advis

-0.64

 sacrament

-0.63

 incorpor

-0.63

 Savings

-0.62

 Tess

-0.61

POSITIVE LOGITS

bour

0.75

haired

0.72

acist

0.70

ignty

0.70

bid

0.69

cin

0.69

idding

0.68

cers

0.67

acists

0.66

casting

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.