INDEX

Explanations

terms related to strategies and their classifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 strategy

-2.86

 Strategy

-2.56

strategy

-2.52

Strategy

-2.42

 STRATEGY

-2.28

 strategies

-2.19

 estrategia

-2.00

 stratégie

-1.98

 Strategies

-1.98

 Strategie

-1.91

POSITIVE LOGITS

DeleteBehavior

0.78

]")]

0.78

ViewFeatures

0.76

prüche

0.74

findpost

0.73

 indisponible

0.73

UTERS

0.73

 Catawiki

0.70

Décès

0.69

complexType

0.68

Activations Density 0.137%

terms related to strategies and their classifications in various contexts

No Comments

No Known Activations