INDEX

Explanations

negations or the word "not."

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

 insuffisamment

-0.56

 cannot

-0.51

Organisateur

-0.49

 tidak

-0.45

 concluded

-0.44

 even

-0.43

 ikke

-0.43

 không

-0.43

 occasionally

-0.42

non

-0.41

POSITIVE LOGITS

buy

0.57

Screen

0.56

not

0.52

Moon

0.51

:✨

0.50

crops

0.50

moon

0.49

Theme

0.49

proposition

0.49

 noDo

0.49

Activations Density 0.475%

negations or the word "not."

No Comments

No Known Activations