INDEX

Explanations

instances of the word "so" and its variations, indicating a focus on intensifiers and modifiers in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

QMetaType

-0.72

 onCreateView

-0.54

󠁮

-0.52

 Pech

-0.51

audrait

-0.51

@"/

-0.50

onViewCreated

-0.48

Ef

-0.48

 Reverso

-0.47

ˎ

-0.47

POSITIVE LOGITS

 ABBREVIATIONS

0.71

lerc

0.68

$_['

0.64

誓

0.58

 pledges

0.58

ghen

0.56

 సౌకర్య

0.56

icolor

0.56

 expectation

0.55

 createSprite

0.54

Activations Density 0.258%

instances of the word "so" and its variations, indicating a focus on intensifiers and modifiers in the text

No Comments

No Known Activations