INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

tein

-0.77

amiya

-0.71

 Thrust

-0.65

ROR

-0.65

dq

-0.65

rade

-0.64

REF

-0.64

ELF

-0.63

ESA

-0.63

anooga

-0.62

POSITIVE LOGITS

orthodox

0.70

 ingred

0.64

peer

0.62

iqueness

0.62

metic

0.61

0000000000000000

0.61

leans

0.60

deals

0.60

gments

0.60

mbuds

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.