INDEX

Explanations

key terms and phrases related to detailed explanations and technical documentation

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

additional information (e.g., appendices, tables)

np_acts-logits-general · gemini-2.0-flash

information provided or found

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

期刊论文

-0.80

expandindo

-0.78

initComponents

-0.75

]")]

-0.75

 BrowserModule

-0.75

 disambiguazione

-0.71

SBATCH

-0.71

WithIOException

-0.70

 виправивши

-0.70

parsedMessage

-0.69

POSITIVE LOGITS

 provided

0.65

 below

0.60

 fournies

0.55

LETON

0.55

 forthcoming

0.53

 supplied

0.52

 available

0.52

 findest

0.52

provided

0.50

 given

0.48

Activations Density 0.421%

key terms and phrases related to detailed explanations and technical documentation

additional information (e.g., appendices, tables)

information provided or found

No Comments

No Known Activations