INDEX

Explanations

references to political elections, specifically related to candidates being elected or inaugurated

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

Follows "was" and precedes election-related terms

np_acts-logits-general · gemini-2.0-flash

was elected

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 محفوظة

-0.71

ArgumentParser

-0.70

 متعلقه

-0.65

__(/*!

-0.64

 يتيمه

-0.58

 saites

-0.57

 dries

-0.57

 nargin

-0.57

']>

-0.57

 resourceCulture

-0.55

POSITIVE LOGITS

 elected

1.23

elected

0.99

 sworn

0.94

 election

0.92

 Elected

0.88

 elect

0.88

 inauguration

0.88

 reelection

0.85

 installed

0.82

 electing

0.81

Activations Density 0.302%

references to political elections, specifically related to candidates being elected or inaugurated

Follows "was" and precedes election-related terms

was elected

No Comments

No Known Activations