INDEX

Explanations

references to news programming and broadcasting entities

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

News sources such as ABC, CBS, and NBC

np_acts-logits-general · gemini-2.0-flash

ABC, ESPN, Disney

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.62

دانشنامهٔ

-0.59

Хьажоргаш

-0.52

HostException

-0.52

 Roskov

-0.50

 estekak

-0.49

awtextra

-0.48

 للاسماء

-0.48

MemoryWarning

-0.47

 kasarigan

-0.47

POSITIVE LOGITS

ABC

0.87

ABC

0.82

 Disney

0.67

Disney

0.65

abc

0.62

Abc

0.61

abc

0.57

 ESPN

0.53

ディズニー

0.52

ESPN

0.51

Activations Density 0.134%

references to news programming and broadcasting entities

News sources such as ABC, CBS, and NBC

ABC, ESPN, Disney

No Comments

No Known Activations