INDEX

Explanations

technical terms and actions related to software development and web deployment

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

reading and listening

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Administrativna

-0.63

Carriera

-0.60

 himo

-0.57

uxxxx

-0.55

 egiten

-0.54

 alimentaires

-0.52

 bezeichneter

-0.52

 françaises

-0.51

irmar

-0.51

POSITIVE LOGITS

 listening

0.59

SupportActionBar

0.58

addCriterion

0.58

 listen

0.57

webElementGuid

0.57

 perpetuity

0.56

AttributeSet

0.56

 BorderSide

0.56

Discografia

0.55

Listening

0.54

Activations Density 0.007%

technical terms and actions related to software development and web deployment

reading and listening

No Comments

No Known Activations