INDEX

Explanations

references to caregiving and caregiver behaviors

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

Regression models and statistical analyses

np_acts-logits-general · gemini-2.0-flash

logistic regression models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 NSCoder

-0.71

 oprot

-0.69

Salta

-0.62

ListActivity

-0.57

 initialState

-0.53

ChildScrollView

-0.49

 kres

-0.49

ɚ

-0.49

{?>

-0.48

 deque

-0.48

POSITIVE LOGITS

 regression

0.93

 regressions

0.83

 models

0.79

 model

0.78

 logistic

0.77

 explanatory

0.76

 covariates

0.75

regression

0.74

 Regression

0.74

 predictors

0.72

Activations Density 1.742%

references to caregiving and caregiver behaviors

Regression models and statistical analyses

logistic regression models

No Comments

No Known Activations