INDEX

Explanations

terms related to military operations and conflicts in specific regions, particularly Afghanistan and Iraq

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ppelin

-0.57

 иск

-0.54

Mag

-0.54

PMID

-0.53

readObject

-0.50

ברו

-0.49

⏜

-0.48

킵

-0.48

SUCCEEDED

-0.48

itself

-0.47

POSITIVE LOGITS

 Afghanistan

0.85

 Kabul

0.83

 AssemblyProduct

0.83

 Afghan

0.83

Afghan

0.82

Afghanistan

0.81

ⓧ

0.81

WithMany

0.80

 Kosovo

0.79

 protoimpl

0.77

Activations Density 2.918%

terms related to military operations and conflicts in specific regions, particularly Afghanistan and Iraq

No Comments

No Known Activations