INDEX

Explanations

references to mathematical models and their applications

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

models and modelling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

gento

-0.52

conio

-0.51

 Crying

-0.49

Sharper

-0.49

Precious

-0.48

música

-0.48

extrême

-0.47

eternal

-0.47

 contemporaine

-0.47

 Constipation

-0.47

POSITIVE LOGITS

ArgumentParser

0.76

 ExecuteAsync

0.74

 model

0.73

 Model

0.67

 Models

0.63

 models

0.60

model

0.60

 MODEL

0.59

TagMode

0.57

 MODELS

0.55

Activations Density 0.057%

references to mathematical models and their applications

models and modelling

No Comments

No Known Activations

references to mathematical models and their applications

models and modelling

No Comments

No Known Activations