INDEX

Explanations

terms related to participants, samples, and variables in studies

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

before "was," "were," or "had."

np_acts-logits-general · gemini-2.0-flash

roles and entities

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

 Мексичка

-0.71

Tikang

-0.70

ValueStyle

-0.69

 AssemblyTitle

-0.62

 GenerationType

-0.61

 AssemblyCulture

-0.59

 ***/

-0.58

 "'");

-0.58

 Normdatei

-0.58

TagMode

-0.57

POSITIVE LOGITS

 utama

0.55

 candidates

0.52

 hereof

0.50

 berupa

0.49

ként

0.48

 inesperado

0.48

 directos

0.48

AccessorTable

0.47

 Kays

0.46

 gynhyrchwyd

0.46

Activations Density 1.065%

terms related to participants, samples, and variables in studies

before "was," "were," or "had."

roles and entities

No Comments

No Known Activations