INDEX

Explanations

instances of the word "report" and its variations

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

"report" or "reports"

np_acts-logits-general · gemini-2.0-flash

reports of findings

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 cewek

-0.46

infinity

-0.45

 szczę

-0.45

 venden

-0.44

 שוליים

-0.44

 connus

-0.43

Ingrédients

-0.43

 transferir

-0.42

yntaxException

-0.42

 personalizar

-0.41

POSITIVE LOGITS

 report

2.20

 Report

2.03

report

1.90

Report

1.85

 reports

1.84

 REPORT

1.78

 Reports

1.70

REPORT

1.56

reports

1.52

Reports

1.49

Activations Density 0.218%

instances of the word "report" and its variations

"report" or "reports"

reports of findings

No Comments

No Known Activations