INDEX

Explanations

references to government officials and their offices

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

Political office/administration

np_acts-logits-general · gemini-2.0-flash

White House, administration, campaign

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

المكان

-0.66

 pinulongan

-0.65

 ब्रेकडाउन

-0.63

windowFixed

-0.60

⟬

-0.58

SharedDtor

-0.57

ⓧ

-0.57

الإنجليزية

-0.55

 poveznice

-0.54

 utafitiHapana

-0.54

POSITIVE LOGITS

CLUYE

0.38

 staf

0.36

 staff

0.35

 entourage

0.34

 administration

0.34

 office

0.33

Office

0.33

cir

0.32

 Office

0.32

administration

0.32

Activations Density 0.313%

references to government officials and their offices

Political office/administration

White House, administration, campaign

No Comments

No Known Activations