INDEX

Explanations

occurrences of actions and events related to sharing and community activities

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

names and historical events

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

 Comunicação

-0.40

vœ

-0.39

 bonheur

-0.35

 pertence

-0.35

 रह

-0.35

Cute

-0.34

 malheur

-0.34

 Eichen

-0.34

bedien

-0.33

itäten

-0.33

POSITIVE LOGITS

Према

0.47

 EconPapers

0.47

PropertyChanging

0.45

QMetaType

0.44

SequentialGroup

0.44

citep

0.44

 arşivlendi

0.41

تفصیلات

0.40

GTCX

0.40

}`}

0.40

Activations Density 0.056%

occurrences of actions and events related to sharing and community activities

names and historical events

No Comments

No Known Activations