INDEX

Explanations

mentions of "Los Angeles."

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

"Los Angeles"

np_acts-logits-general · gemini-2.0-flash

Los Angeles

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

 متعلقه

-0.60

 Mihai

-0.56

ască

-0.54

ItemBackground

-0.53

uidado

-0.51

 trattano

-0.50

 hilt

-0.50

dafx

-0.50

 saurait

-0.50

 HasFactory

-0.49

POSITIVE LOGITS

 Angeles

0.96

 doInBackground

0.68

Ang

0.64

 angeles

0.62

 ANGELES

0.61

 angles

0.58

AddTagHelper

0.58

Анд

0.57

 Ange

0.56

 Angles

0.56

Activations Density 0.081%

mentions of "Los Angeles."

"Los Angeles"

Los Angeles

No Comments

No Known Activations