INDEX

Explanations

references to "deep learning" and related concepts

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

deep learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

带宽

-0.33

umumkan

-0.33

 Мексичка

-0.32

 scaricare

-0.30

 possíveis

-0.30

 attorno

-0.30

 opge

-0.29

 dessas

-0.29

 posibles

-0.29

єра

-0.29

POSITIVE LOGITS

 Deep

0.88

Deep

0.88

DEEP

0.86

 deep

0.86

deep

0.83

 DEEP

0.82

 dive

0.67

深

0.67

深

0.66

Shallow

0.62

Activations Density 0.010%

references to "deep learning" and related concepts

deep learning

No Comments

No Known Activations