INDEX

Explanations

references to political figures and events, particularly related to judicial nominations and partisan actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 чел

-0.55

Ti

-0.55

choenen

-0.53

łaś

-0.53

SceneManagement

-0.52

 Kahn

-0.52

tować

-0.51

skapet

-0.51

Elton

-0.50

افته

-0.50

POSITIVE LOGITS

 Baillargeon

0.79

pyplot

0.71

0.70

 itſelf

0.67

 fingerprints

0.67

 متعلقه

0.66

 Mitter

0.64

 Ging

0.64

 doInBackground

0.63

 Fingerprint

0.62

Activations Density 2.829%

references to political figures and events, particularly related to judicial nominations and partisan actions

No Comments

No Known Activations