INDEX

Explanations

terms related to scientific analysis and statistical evaluation

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

followed by how something was studied/determined

np_acts-logits-general · gemini-2.0-flash

scientific investigation and analysis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulongan

-0.54

webElementXpaths

-0.53

labus

-0.50

oredCriteria

-0.49

WebElementEntity

-0.47

 קט

-0.47

öh

-0.47

LikeLike

-0.46

 VIDEOTAPE

-0.46

unex

-0.46

POSITIVE LOGITS

 separately

0.63

 using

0.58

 analytically

0.55

 retrospec

0.53

 through

0.52

脚注の使い方

0.52

Schemes

0.51

 acuer

0.51

WebVitals

0.50

stdafx

0.50

Activations Density 1.026%

terms related to scientific analysis and statistical evaluation

followed by how something was studied/determined

scientific investigation and analysis

No Comments

No Known Activations