INDEX

Explanations

statistical data related to approval and disapproval ratings, particularly in political contexts

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

approval ratings and polls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 autorytatywna

-0.62

OGND

-0.50

Personendaten

-0.50

 Holman

-0.44

LookAnd

-0.44

 Finney

-0.44

/\.

-0.43

URLException

-0.43

FormBuilder

-0.43

ImageContext

-0.41

POSITIVE LOGITS

 Paglinawan

0.51

 polls

0.40

 encuesta

0.39

biskan

0.37

jestic

0.36

uoja

0.36

tagext

0.36

OrBuilder

0.35

 Stimmung

0.35

toprule

0.35

Activations Density 0.067%

statistical data related to approval and disapproval ratings, particularly in political contexts

approval ratings and polls

No Comments

No Known Activations