INDEX

Explanations

language related to exaggeration and theatricality

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

guro

-0.39

principalTable

-0.38

jalá

-0.38

 estekak

-0.38

AutoModerator

-0.38

sproz

-0.37

 trơn

-0.37

 lamang

-0.34

Thread

-0.34

 Erosion

-0.34

POSITIVE LOGITS

 exaggerated

0.76

夸张

0.74

 exaggerate

0.74

 exaggerating

0.73

 exaggeration

0.70

 dram

0.68

 dramatic

0.65

 exager

0.65

 iNdEx

0.61

 exagger

0.60

Activations Density 0.389%

language related to exaggeration and theatricality

No Comments

No Known Activations