INDEX

Explanations

references to historical significance or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hist

-0.51

Hist

-0.50

lot

-0.44

vivi

-0.41

.*")]

-0.41

●

-0.41

 upkeep

-0.41

%%

-0.39

 hist

-0.38

dec

-0.38

POSITIVE LOGITS

 historical

0.93

 holy

0.90

historical

0.85

 historic

0.83

 Holy

0.81

Historical

0.81

historic

0.81

 históricas

0.78

Holy

0.77

 historischen

0.77

Activations Density 0.082%

references to historical significance or properties

No Comments

No Known Activations