INDEX

Explanations

mentions of camps and related concepts

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

Autowired

-0.54

 שוליים

-0.46

 AssemblyProduct

-0.45

oshiba

-0.43

 först

-0.43

WebElementEntity

-0.42

Παραπομπές

-0.41

dafrika

-0.41

Sklici

-0.41

Fordítás

-0.41

POSITIVE LOGITS

 camp

2.55

 camps

2.22

 Camp

2.22

Camp

2.17

camp

2.16

 CAMP

2.00

 Camps

1.91

CAMP

1.81

 campamento

1.79

camps

1.75

Activations Density 0.087%

mentions of camps and related concepts

No Comments

No Known Activations