INDEX

Explanations

references to new concepts or experiences that involve change and adaptation

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

Followed by "for"

np_acts-logits-general · gemini-2.0-flash

newness or unfamiliar experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ionista

-0.43

 fidé

-0.40

setVerticalGroup

-0.38

ChildScrollView

-0.38

ómicas

-0.37

 canina

-0.36

haustible

-0.35

værende

-0.35

risi

-0.35

 Rossa

-0.35

POSITIVE LOGITS

 unfamiliar

1.06

 unacc

0.81

 ungew

0.62

 accustomed

0.61

陌

0.58

 inexperienced

0.56

慣れて

0.55

慣

0.55

初めての

0.55

ustomed

0.55

Activations Density 0.365%

references to new concepts or experiences that involve change and adaptation

Followed by "for"

newness or unfamiliar experience

No Comments

No Known Activations

references to new concepts or experiences that involve change and adaptation

Followed by "for"

newness or unfamiliar experience

No Comments

No Known Activations