INDEX

Explanations

terms and phrases associated with predictive modeling and statistical analysis related to neural networks

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

the neuron detects salient content words—domain-specific nouns and technical keywords (important topic words) rather than function words.

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

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

AnimationsModule

-0.48

ttemberg

-0.47

 Photocase

-0.47

icksburg

-0.46

Scalars

-0.45

AutoresizingMask

-0.45

፩

-0.45

 ligiloj

-0.45

↻

-0.45

はじめに

-0.44

POSITIVE LOGITS

 <=",

0.42

 Chwiliwch

0.35

JNIEnv

0.35

 ويكيپيديا

0.34

 Heaven

0.33

ྣ

0.33

 Italijani

0.33

utilisons

0.32

 चीज़ों

0.32

 weak

0.31

Activations Density 0.359%

terms and phrases associated with predictive modeling and statistical analysis related to neural networks

the neuron detects salient content words—domain-specific nouns and technical keywords (important topic words) rather than function words.

No Comments

No Known Activations

terms and phrases associated with predictive modeling and statistical analysis related to neural networks

the neuron detects salient content words—domain-specific nouns and technical keywords (important topic words) rather than function words.

No Comments

No Known Activations