INDEX

Explanations

terms related to studies and research projects

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

for undertakings: study, project, program

np_acts-logits-general · gemini-2.0-flash

organized projects, entities, or publications

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

Negative Logits

الإنجليزية

-0.59

InjectAttribute

-0.56

ASTE

-0.55

انيف

-0.54

 ComVisible

-0.54

 дописавши

-0.54

hages

-0.54

 mergeFrom

-0.53

 nakalista

-0.52

 Normdatei

-0.52

POSITIVE LOGITS

 itself

0.74

Enllaces

0.65

 kendisi

0.59

énario

0.59

টি

0.58

 nargin

0.55

 journée

0.54

⭒

0.52

$__

0.52

/*

0.51

Activations Density 0.788%

terms related to studies and research projects

for undertakings: study, project, program

organized projects, entities, or publications

No Known Activations