INDEX

Explanations

references to Android app support classes and libraries

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

<start_of_turn>user sequences

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

MockMvc

-0.25

tagHelperRunner

-0.24

 amid

-0.24

 cheminée

-0.23

 seks

-0.23

 followed

-0.23

 unto

-0.22

Thro

-0.22

LLocation

-0.21

 επικ

-0.21

POSITIVE LOGITS

 GenerationType

0.71

 Италијани

0.66

 estekak

0.66

ValueStyle

0.64

endpush

0.64

icordia

0.63

AnimationsModule

0.62

tonsoft

0.60

 NSCoder

0.60

adaptiveStyles

0.60

Activations Density 0.000%

references to Android app support classes and libraries

<start_of_turn>user sequences

No Comments

No Known Activations