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

 Osiris

-0.67

 Terra

-0.66

 Horus

-0.66

Vel

-0.66

zona

-0.65

 GOODMAN

-0.64

 Vector

-0.64

 escaped

-0.64

Hav

-0.63

away

-0.60

POSITIVE LOGITS

icultural

0.86

ipolar

0.83

 handshake

0.81

hower

0.78

draft

0.70

geist

0.70

cloth

0.67

schild

0.66

ike

0.66

alm

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.