INDEX

Explanations

technical terms and functions related to programming and scientific analysis

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

code or citation indicators

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

GetAsync

-0.62

 uska

-0.54

 Natale

-0.45

 Bourgoin

-0.45

 newVal

-0.44

 ngoại

-0.44

ISupport

-0.44

jini

-0.43

 afirm

-0.42

 Eaton

-0.42

POSITIVE LOGITS

Kaynakça

0.79

 الحره

0.76

 GenerationType

0.68

IContainer

0.68

SourceChecksum

0.65

:✨

0.63

Cyfarwyddwr

0.62

IntoConstraints

0.61

RegressionTest

0.59

mazoo

0.58

Activations Density 0.240%

technical terms and functions related to programming and scientific analysis

code or citation indicators

No Comments

No Known Activations