INDEX

Explanations

programming-related constructs, particularly function definitions and variable manipulations

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

Code-related syntax

np_acts-logits-general · gemini-2.0-flash

code and math symbols

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

 ujednoznacz

-0.70

Diweddarwch

-0.69

 disambiguazione

-0.61

RegressionTest

-0.60

SuspendLayout

-0.60

sizeCache

-0.60

 Signalez

-0.59

 للاسماء

-0.58

homonymie

-0.56

 nakalista

-0.55

POSITIVE LOGITS

abstractmethod

0.54

URIComponent

0.36

 virtual

0.36

 bire

0.36

 htons

0.35

 DevComponents

0.34

eti

0.34

ToBounds

0.34

virtual

0.33

不然

0.33

Activations Density 1.044%

programming-related constructs, particularly function definitions and variable manipulations

Code-related syntax

code and math symbols

No Comments

No Known Activations