INDEX

Explanations

specific terms related to writing, programming, and general organizational tasks

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

how to / questions about

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

the neuron activates for prominent topical content words (key nouns or subject words) in the text.

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

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

principalColumn

-0.56

 insuffisamment

-0.55

 CreateTagHelper

-0.47

pholes

-0.42

elemField

-0.39

defn

-0.39

prefixer

-0.39

bootstrapcdn

-0.38

 cref

-0.38

исленность

-0.38

POSITIVE LOGITS

 Reſ

0.51

 ſte

0.50

GOTREF

0.48

ThemeOverlay

0.46

 myſelf

0.46

 AssemblyCulture

0.44

$_(

0.43

arriver

0.43

 purpoſe

0.42

 faſt

0.42

Activations Density 0.215%

specific terms related to writing, programming, and general organizational tasks

how to / questions about

the neuron activates for prominent topical content words (key nouns or subject words) in the text.

No Comments

No Known Activations