INDEX

Explanations

references to interpersonal relationships and emotions

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

BCC

-0.50

MigrationBuilder

-0.49

 disgra

-0.49

arnia

-0.47

hdashline

-0.46

MOP

-0.46

MathML

-0.46

opia

-0.46

assies

-0.45

MTC

-0.45

POSITIVE LOGITS

 spouse

0.56

 pareja

0.56

 partner

0.54

 husband

0.51

 wife

0.51

 parejas

0.50

 pasangan

0.48

 marriage

0.47

 همسر

0.45

 Wife

0.44

Activations Density 0.143%

references to interpersonal relationships and emotions

No Comments

No Known Activations