INDEX

Explanations

technical terms and parameters related to image processing and data visualization

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

Filename extensions or image tags

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

TypedDataSet

-0.42

ImageContext

-0.42

">😂

-0.40

󠁢

-0.39

 دیکھیے

-0.36

hoeddwyd

-0.36

 Roskov

-0.36

 Normdatei

-0.36

ConstraintMaker

-0.36

Chham

-0.36

POSITIVE LOGITS

 spatially

0.63

 averaged

0.61

 perturbed

0.59

 plots

0.57

 computationally

0.56

 dimensionality

0.54

 calibrated

0.54

 geometries

0.54

 plot

0.53

 numerically

0.53

Activations Density 2.310%

technical terms and parameters related to image processing and data visualization

Filename extensions or image tags

No Comments

No Known Activations