INDEX

Explanations

instances and variations of the word "scan" and related terms associated with scanning processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 AssemblyCulture

-0.83

+/**

-0.81

 eccell

-0.78

 Pyle

-0.74

 CURIAM

-0.74

oplayer

-0.71

 kasarigan

-0.71

 detalhes

-0.70

accordo

-0.70

 dettagli

-0.69

POSITIVE LOGITS

 scan

1.78

 Scan

1.65

 SCAN

1.56

SCAN

1.52

Scan

1.51

 scans

1.51

 scanning

1.50

 scanner

1.48

scan

1.48

 scanned

1.35

Activations Density 0.074%

instances and variations of the word "scan" and related terms associated with scanning processes

No Comments

No Known Activations