INDEX

Explanations

specific structured linguistic elements indicating importance or emphasis

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

There seems to be, I just want

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

UnitTesting

-0.61

ſelf

-0.55

 ſtre

-0.50

ſchen

-0.49

centralwidget

-0.48



-0.48

KommentareTeilen

-0.47

 ſich

-0.47

 ſche

-0.47

ſcher

-0.46

POSITIVE LOGITS

Хьажоргаш

0.45

Rè

0.44

 følge

0.41

 tarde

0.41

 rekke

0.39

よいよ

0.38

 retenir

0.36

 Keuangan

0.36

bbene

0.35

￡

0.35

Activations Density 0.001%

specific structured linguistic elements indicating importance or emphasis

There seems to be, I just want

No Comments

No Known Activations

specific structured linguistic elements indicating importance or emphasis

There seems to be, I just want

No Comments

No Known Activations