INDEX

Explanations

references to evidence and facts in various contexts

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

facts and competition

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

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

findOneAndUpdate

-0.32

 населён

-0.29

 isang

-0.28

 görüntüsü

-0.28

nestjs

-0.28

 bulundu

-0.28

 fusion

-0.28

似た

-0.27

めていた

-0.27

對於

-0.27

POSITIVE LOGITS

GEBURTSDATUM

0.77

PerformLayout

0.66

 betweenstory

0.65

yntaxException

0.64

ViewImports

0.63

principalColumn

0.61

 sumpay

0.61

msgSender

0.59

ToProps

0.57

MessageTagHelper

0.56

Activations Density 0.119%

references to evidence and facts in various contexts

facts and competition

No Comments

No Known Activations