INDEX

Explanations

programming classes and structures related to API requests and frameworks

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

Code-related structural elements

np_acts-logits-general · gemini-2.0-flash

super(...) context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

+#+#

-0.80

IndentedString

-0.67

новниш

-0.66

 onData

-0.66

CloseOperation

-0.66

tagHelperRunner

-0.65

tableFuture

-0.64

 MaterialApp

-0.64

GraphicsUnit

-0.63

%"),

-0.63

POSITIVE LOGITS

Compat

0.50

 automatica

0.45

 oiseaux

0.44

 vectoriales

0.43

mybatisplus

0.42

JEL

0.42

 climati

0.42

 accepte

0.42

 combusti

0.41

 whisper

0.41

Activations Density 0.066%

programming classes and structures related to API requests and frameworks

Code-related structural elements

super(...) context

No Comments

No Known Activations