INDEX

Explanations

terms related to message duration within a software context

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

conditions of any KIND

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

fjspx

-0.68

 /\.(

-0.60

(&:

-0.56

InjectMocks

-0.54

RenderAtEndOf

-0.52

Clik

-0.52

__(/*!

-0.50

aarrggbb

-0.50

">—

-0.50

ină

-0.50

POSITIVE LOGITS

gonic

0.70

 AssemblyCompany

0.63

 türkiye

0.61

BufferException

0.59

ytale

0.57

ousand

0.56

EDEFAULT

0.56

ględ

0.55

 propTypes

0.54

tagHelperRunner

0.54

Activations Density 0.002%

terms related to message duration within a software context

conditions of any KIND

No Comments

No Known Activations