INDEX

Explanations

technical jargon and function-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

BeginContext

-0.62

 >=",

-0.62

 GenerationType

-0.59

 onResponse

-0.59

 AttributeSet

-0.58

IsInitialized

-0.57

 disambiguazione

-0.56

 akka

-0.56

 illuminated

-0.54

DoubleQuotes

-0.54

POSITIVE LOGITS

mişti

0.64

KEYCODE

0.47

 жест

0.46

AsUp

0.46

 burn

0.45

 dési

0.42

 IActionResult

0.41

 nhà

0.41

 chi̍t

0.41

 região

0.41

Activations Density 0.833%

technical jargon and function-related terms

No Comments

No Known Activations