INDEX

Explanations

terms related to categories, classifications, and evaluations

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

a process or concept

np_acts-logits-general · gemini-2.0-flash

processes, validation, and results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.88

 للمعارف

-0.74

 تانيه

-0.71

Aiheesta

-0.71

GEBURTSDATUM

-0.71

+#+#

-0.68

 المعيارى

-0.68

قایناقلار

-0.68

EndContext

-0.67

 GenerationType

-0.67

POSITIVE LOGITS

OfThe

0.51

 autem

0.51

Wise

0.49

OnThe

0.47

Man

0.47

setz

0.46

InThe

0.46

面

0.45

Gov

0.45

ſelf

0.45

Activations Density 1.392%

terms related to categories, classifications, and evaluations

a process or concept

processes, validation, and results

No Comments

No Known Activations