INDEX

Explanations

specific names or terms associated with individuals or entities, often in a context of attribution or reference

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

orogastric, Osorio, Zorov, Darroti

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

basicConfig

-0.52

DataAnnotations

-0.51

 grecque

-0.49

 GRATU

-0.46

printStackTrace

-0.46

 accro

-0.45

 ultimate

-0.45

 artistique

-0.45

 chrétienne

-0.44

hdysval

-0.44

POSITIVE LOGITS

oden

0.71

oto

0.68

ode

0.66

oi

0.66

orio

0.66

od

0.65

olo

0.63

og

0.63

oso

0.63

oz

0.62

Activations Density 1.861%

specific names or terms associated with individuals or entities, often in a context of attribution or reference

orogastric, Osorio, Zorov, Darroti

No Comments

No Known Activations

specific names or terms associated with individuals or entities, often in a context of attribution or reference

orogastric, Osorio, Zorov, Darroti

No Comments

No Known Activations