INDEX

Explanations

references to political adversaries and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Ibid

-0.45

 tròn

-0.44

 Grades

-0.44

ValueStyle

-0.44

 guida

-0.43

frontier

-0.42

 Grade

-0.41

thood

-0.41

 dimas

-0.41

 GlobalKey

-0.41

POSITIVE LOGITS

 opponent

0.90

 opponents

0.85

 rival

0.83

 adversary

0.78

 opposing

0.76

 Rival

0.74

rival

0.73

opponent

0.73

 Gegner

0.72

 rivals

0.71

Activations Density 0.677%

references to political adversaries and conflicts

No Comments

No Known Activations