INDEX

Explanations

the occurrence of the word "la" or its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RectangleBorder

-0.77

numerusform

-0.56

 itſelf

-0.52

 Putih

-0.50

complexContent

-0.48

 BoxFit

-0.47

 كومونز

-0.46

ėmis

-0.45

 conmigo

-0.45

tonsoft

-0.45

POSITIVE LOGITS

 ла

1.95

 Ла

1.86

la

1.80

Ла

1.75

Lac

1.75

Laf

1.65

lac

1.63

Lah

1.63

Laz

1.62

La

1.61

Activations Density 0.845%

the occurrence of the word "la" or its variations in different contexts

No Comments

No Known Activations