INDEX

Explanations

affirmations or confirmations of current states or opinions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 McKinnon

-1.07

CMYK

-0.86

 okuyayım

-0.86

Hauptartikel

-0.86

期刊论文

-0.85

WireFormatLite

-0.85

__":

-0.84

jména

-0.84

OSSARY

-0.83

NameInMap

-0.83

POSITIVE LOGITS

 RIGHT

1.18

right

1.17

 Right

1.12

 right

1.12

RIGHT

1.08

Right

1.06

setRight

1.03

getRight

0.96

 righ

0.93

 Righ

0.92

Activations Density 0.118%

affirmations or confirmations of current states or opinions

No Comments

No Known Activations