INDEX

Explanations

terms related to military honors and decorations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

FormTagHelper

-1.08

 surla

-0.95

 BoxFit

-0.93

 esternos

-0.87

 سكانية

-0.86

 >=",

-0.85

 Roskov

-0.83

NewUrlParser

-0.79

tagHelperRunner

-0.79

edn

-0.78

POSITIVE LOGITS

勲

0.56

 Medal

0.47

 medals

0.47

decoración

0.46

 awards

0.46

0.45

勋

0.45

 awarded

0.44

popper

0.43

Activations Density 0.059%

terms related to military honors and decorations

No Comments

No Known Activations