INDEX

Explanations

discussions surrounding objections and arguments

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

arguments and excuses

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.74

GEBURTSDATUM

-0.73

 disambiguazione

-0.69

 purpoſe

-0.67

 queſta

-0.67

 Reſ

-0.66

 للاسماء

-0.66

 GenerationType

-0.65

 ModelExpression

-0.63

rungsseite

-0.63

POSITIVE LOGITS

 argument

0.67

 arguments

0.60

 excuses

0.54

 argue

0.51

 Argument

0.50

 argumentos

0.49

argument

0.49

 excuse

0.48

 objections

0.47

 argued

0.47

Activations Density 0.162%

discussions surrounding objections and arguments

arguments and excuses

No Comments

No Known Activations