INDEX

Explanations

specific named entities and important terms related to particular subjects or contexts

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

names of people and places

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

 FetchType

-0.54

__*/

-0.52

 Been

-0.52

 been

-0.52

been

-0.51

Numerade

-0.51

 Ethiopian

-0.50

IBAction

-0.50

 Wanna

-0.50

 ActivatedRoute

-0.49

POSITIVE LOGITS

 GALERÍA

0.56

 Theſe

0.52

 ſtate

0.51

 transparentes

0.51

 น้ำ

0.50

 theſe

0.50

 juſ

0.48

 Nước

0.47

 Internasional

0.47

Transparency

0.47

Activations Density 0.209%

specific named entities and important terms related to particular subjects or contexts

names of people and places

No Comments

No Known Activations