INDEX

Explanations

references or mentions of specific variables or identifiers used in a technical context

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

`start_of_turn` user

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

 estekak

-0.82

 propOrder

-0.69

AsUp

-0.69

SharedDtor

-0.65

tagext

-0.63

 Infórmanos

-0.63

verwijspagina

-0.60

__":

-0.60

Clik

-0.60

 ujednoznacz

-0.60

POSITIVE LOGITS

Identyfik

0.46

 pinulongan

0.38

putAll

0.30

WriteTo

0.30

 poslední

0.29

0.28

 ISNI

0.27

Autoritní

0.26

 року

0.26

 vēl

0.25

Activations Density 0.000%

references or mentions of specific variables or identifiers used in a technical context

`start_of_turn` user

No Comments

No Known Activations