INDEX

Explanations

occurrences of the preposition "to"

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

"to" followed by a verb

np_acts-logits-general · gemini-2.0-flash

to + verb

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

getStart

-0.35

 ressemb

-0.28

 avantage

-0.28

 Independencia

-0.28

 pří

-0.27

 huvud

-0.26

dø

-0.26

 صفحۀ

-0.26

 нес

-0.25

 Liebes

-0.25

POSITIVE LOGITS

ChildScrollView

0.89

 ddelwed

0.83

SBATCH

0.83

rotum

0.82

<unused8>

0.81

[@BOS@]

0.81

<unused41>

0.81

<unused74>

0.81

<unused47>

0.81

<pad>

0.80

Activations Density 0.516%

occurrences of the preposition "to"

"to" followed by a verb

to + verb

No Comments

No Known Activations