INDEX

Explanations

terms related to probability and its distributions

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

probability distribution

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

 aislada

-0.54

 servem

-0.53

 Kers

-0.49

Du

-0.49

 suivez

-0.48

 isolé

-0.48

 vostra

-0.47

 Ander

-0.47

 instalado

-0.47

POSITIVE LOGITS

 probability

1.03

 Probability

0.98

 probab

0.91

Probability

0.88

probability

0.87

 Probab

0.85

 probabil

0.76

Probab

0.75

 probabilities

0.75

proba

0.73

Activations Density 0.019%

terms related to probability and its distributions

probability distribution

No Comments

No Known Activations