INDEX

Explanations

rhetorical questions that seek affirmation or agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

mybatisplus

-0.53



-0.48

 Савезне

-0.45

TestingModule

-0.44

gameserver

-0.43

HasAnnotation

-0.41

ngilizce

-0.39

detalles

-0.39

hlin

-0.38

siers

-0.38

POSITIVE LOGITS

offsetof

0.47

 &___

0.43

 HFILL

0.41

huh

0.41

 endforeach

0.41

ませんか

0.40

 snippetHide

0.40

是吗

0.40

appellant

0.40

Javadoc

0.39

Activations Density 0.110%

rhetorical questions that seek affirmation or agreement

No Comments

No Known Activations