INDEX

Explanations

personal pronouns and expressions of self-identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 CascadeType

-0.62

 صوتيه

-0.55

/**

-0.54

 createSlice

-0.54

casus

-0.54

ValueStyle

-0.53

edas

-0.53

berus

-0.52

 الرياضيه

-0.51

kowitz

-0.51

POSITIVE LOGITS

 Maureen

0.41

 gonna

0.40

ìm

0.39

Uro

0.38

 вагі

0.38

്‍

0.38

Exhaust

0.37

Wim

0.37

 Exhaust

0.37

 exhaust

0.37

Activations Density 0.103%

personal pronouns and expressions of self-identity

No Comments

No Known Activations