INDEX

Explanations

references to notable individuals and their achievements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

notable people

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

The neuron detects headings or phrases that introduce lists of notable people (e.g., "Notable people"/"Notable persons" and similar list-introduction 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

Negative Logits

tanleria

-0.41

 zákaz

-0.41

magitan

-0.40

 atlik

-0.39

 Möglich

-0.39

PerformLayout

-0.39

 terapé

-0.38

 때문

-0.38

 tradisi

-0.37

 Eigentü

-0.37

POSITIVE LOGITS

 celebrities

0.59

ModelSerializer

0.59

nalités

0.58

InjectAttribute

0.55

 أعلام

0.53

 eminence

0.52

 personalities

0.50

 celebrity

0.49

 celebs

0.49

 eminent

0.49

Activations Density 0.341%

references to notable individuals and their achievements

notable people

The neuron detects headings or phrases that introduce lists of notable people (e.g., "Notable people"/"Notable persons" and similar list-introduction text).

No Known Activations

references to notable individuals and their achievements

notable people

The neuron detects headings or phrases that introduce lists of notable people (e.g., "Notable people"/"Notable persons" and similar list-introduction text).

No Known Activations