INDEX

Explanations

terms referring to defining characteristics or properties

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

characteristic followed by a noun

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

wapV

-0.44

 Fairbanks

-0.44

 marié

-0.42

 تانيه

-0.41

毆

-0.40

devamını

-0.40

å

-0.40

itonitis

-0.39

ougou

-0.39

 MONEY

-0.38

POSITIVE LOGITS

 characteristic

2.05

characteristic

1.85

Characteristic

1.84

 Characteristic

1.79

 caractéristique

1.14

 característica

1.00

 caratter

0.96

 характер

0.93

 charakterysty

0.89

 caracter

0.80

Activations Density 0.012%

terms referring to defining characteristics or properties

characteristic followed by a noun

No Comments

No Known Activations