INDEX

Explanations

numerical or quantitative data and related operations in a technical context

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

random characters and numbers

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

the

-0.38

or

-0.34

↵

-0.34

 that

-0.33

is

-0.33

 person

-0.32

mathrm

-0.32

st

-0.32

ed

-0.31

POSITIVE LOGITS

 betweenstory

1.17

fromnode

0.88

 pinulongan

0.85

 Meksiku

0.83

 يتيمه

0.82

OGND

0.82

 ویکی‌پدی

0.80

tonode

0.80

ArrowToggle

0.79

 Numerade

0.78

Activations Density 0.238%

numerical or quantitative data and related operations in a technical context

random characters and numbers

No Comments

No Known Activations