INDEX

Explanations

terms related to adding elements or listeners in a programming context

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

`add` calls followed by a listener

np_acts-logits-general · gemini-2.0-flash

adding listeners or programmatic elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 الدولى

-0.64

تقاوى

-0.61

ContentAsync

-0.60

 AssemblyCompany

-0.59

+#+#

-0.58

 otomatig

-0.58

featureID

-0.58

 ragioni

-0.56

stdc

-0.55

 AssemblyProduct

-0.55

POSITIVE LOGITS

endum

0.76

ressed

0.65

iction

0.65

ressee

0.63

 Ababa

0.61

icted

0.60

TagHelper

0.58

resse

0.57

 Adds

0.57

rinfo

0.55

Activations Density 0.042%

terms related to adding elements or listeners in a programming context

`add` calls followed by a listener

adding listeners or programmatic elements

No Comments

No Known Activations