INDEX

Explanations

references to personal experiences and emotional states

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

Prepositions followed by possessive pronouns

np_acts-logits-general · gemini-2.0-flash

idiomatic phrases

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

exitRule

-0.68

UnusedPrivate

-0.67

Хьажоргаш

-0.64

 Administrativna

-0.56

ModelAdmin

-0.55

Diwedd

-0.52

 استنادى

-0.49

 kaynağından

-0.49

 Ausblick

-0.48

 للاسماء

-0.48

POSITIVE LOGITS

 proverbial

0.72

 metaphorical

0.46

AddTagHelper

0.40

 coals

0.37

 stethoscope

0.37

 fenders

0.35

afficheront

0.35

 smokes

0.35

 celana

0.35

Aantal

0.34

Activations Density 0.245%

references to personal experiences and emotional states

Prepositions followed by possessive pronouns

idiomatic phrases

No Comments

No Known Activations