INDEX

Explanations

elements related to political manipulation and control over narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 regia

-0.48

nextLine

-0.45

AllowAnonymous

-0.44

 positivo

-0.43

Commons

-0.41

URLException

-0.41

 gelassen

-0.40

ParallelGroup

-0.39

 virtues

-0.39

ŋ

-0.39

POSITIVE LOGITS

 liever

0.71

RegressionTest

0.65

 ***!

0.64

QMetaType

0.59

konos

0.59

 graag

0.58

 unbedingt

0.58

dersfield

0.57

脚注の使い方

0.55

EndGlobalSection

0.55

Activations Density 0.380%

elements related to political manipulation and control over narratives

No Comments

No Known Activations