INDEX

Explanations

references to California and related entities, indicating a focus on geographic or state-specific 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 @ 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

 morts

-0.44

cheln

-0.43

printer

-0.43

Hunger

-0.42

 printers

-0.42

 printer

-0.41

kste

-0.41

 hole

-0.41

wj

-0.41

 useDispatch

-0.41

POSITIVE LOGITS

 California

1.76

California

1.64

 CALIFORNIA

1.54

 california

1.41

 Californian

1.36

 Califor

1.32

california

1.30

CALIFORNIA

1.29

 Californie

1.27

 Kalifor

1.25

Activations Density 0.127%

references to California and related entities, indicating a focus on geographic or state-specific contexts

No Comments

No Known Activations