INDEX

Explanations

elements related to the plot and characters of a narrative

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

casting and titles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ValueStyle

-0.46

ंदीखरीदारी

-0.43

]]

-0.40

}>;

-0.39

 nahilalakip

-0.39

الحياه

-0.38

 eastward

-0.38

}))

-0.37

 ISNI

-0.34

 становника

-0.34

POSITIVE LOGITS

tagHelperRunner

0.53

 getItemId

0.50

хьтан

0.50

MarshalTo

0.49

 teleno

0.48

LogError

0.45

MemoryWarning

0.45

הערות

0.44

 prés

0.42

visão

0.42

Activations Density 0.009%

elements related to the plot and characters of a narrative

casting and titles

No Comments

No Known Activations