INDEX

Explanations

references to international relations and geopolitical conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

opsida

-0.61

########.

-0.60

avra

-0.58

 anonim

-0.53

Espèce

-0.51

geslacht

-0.51

prepareStatement

-0.51

toppers

-0.50

 décret

-0.49

 Sodom

-0.49

POSITIVE LOGITS

geo

0.86

 geopolitical

0.83

ipolar

0.80

 security

0.73

 multip

0.71

Geo

0.70

geo

0.69

Geo

0.68

 bipolar

0.66

Pivot

0.66

Activations Density 0.315%

references to international relations and geopolitical conflicts

No Comments

No Known Activations