INDEX

Explanations

references to awards and achievements, particularly in professional contexts

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

names and professions

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

 Савезне

-0.55

Спољашње

-0.52

хьтан

-0.49

XmlAccessType

-0.49

 OMITBAD

-0.45

Spoljašnje

-0.44

CARACTERIST

-0.42

astify

-0.42

Diweddarwch

-0.41

hyrchwyd

-0.41

POSITIVE LOGITS

 AssemblyCompany

0.55

AndEndTag

0.54

__*/

0.41

antMatchers

0.40

ownik

0.39

sendFile

0.38

 chanteur

0.38

-------

0.38

 poète

0.38

"]]

0.38

Activations Density 0.022%

references to awards and achievements, particularly in professional contexts

names and professions

No Comments

No Known Activations