INDEX

Explanations

the letter "P" in various contexts

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

Token "P" followed by certain letters

np_acts-logits-general · gemini-2.0-flash

words starting with P

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 quæ

-0.78

 raiſ

-0.66

 omnia

-0.63

 viſ

-0.62

 tranſ

-0.61

 myſelf

-0.59

(!__

-0.59

 Jefus

-0.58

 anſ

-0.58

 LayoutInflater

-0.57

POSITIVE LOGITS

 Chwiliwch

0.60

 particuliers

0.50

0.49

createStatement

0.47

;#

0.47

 estimés

0.46

SID

0.46

 pauvreté

0.45

QtWidgets

0.44

 tanker

0.44

Activations Density 0.478%

the letter "P" in various contexts

Token "P" followed by certain letters

words starting with P

No Comments

No Known Activations