INDEX

Explanations

alphanumeric sequences or identifiers related to technical data or specifications

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

Tokens before numbers

np_acts-logits-general · gemini-2.0-flash

start of user commands

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

/**/*.

-0.43

UseVisualStyle

-0.42

IPv

-0.42

GEBURTS

-0.40

Nationalité

-0.40

 spur

-0.39

 disambiguazione

-0.39

最快更新

-0.39

発

-0.38

 choi

-0.38

POSITIVE LOGITS

 EconPapers

0.52

createStatement

0.46

 ProtoMessage

0.45

 Differenz

0.42

 arreglos

0.42

Попис

0.42

 sugerencias

0.42

chartInstance

0.41

yntaxException

0.41

 descarga

0.40

Activations Density 0.135%

alphanumeric sequences or identifiers related to technical data or specifications

Tokens before numbers

start of user commands

No Comments

No Known Activations