INDEX

Explanations

the word "incorporate" and its variations in different contexts

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

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

GEBURTSDATUM

-0.77

SEGUIR

-0.73

abetes

-0.62

StatusEnum

-0.60

BooleanField

-0.57

makeText

-0.57

ednes

-0.55

 Riproduzione

-0.55

 currentState

-0.55

ſſung

-0.54

POSITIVE LOGITS

 incorporate

0.85

 incorporates

0.79

 incorporated

0.78

 incorporation

0.76

 incorporating

0.75

 incorporar

0.69

 incorporación

0.68

 Incorporation

0.66

 incorpora

0.65

 incorporado

0.65

Activations Density 0.007%

the word "incorporate" and its variations in different contexts

No Comments

No Known Activations