INDEX

Explanations

instances of the word "report" and its variations, suggesting a focus on reporting information or findings within texts

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

"report" or "reported"

np_acts-logits-general · gemini-2.0-flash

reporting 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

Vac

-0.47

Personalized

-0.46

 Belf

-0.46

anganese

-0.45

Enhance

-0.44

anasia

-0.44

 Lindgren

-0.44

vascular

-0.43

wax

-0.43

Exclusive

-0.43

POSITIVE LOGITS

 reported

1.84

 report

1.73

 reporting

1.72

 reports

1.63

report

1.58

reported

1.55

 Reporting

1.52

 Report

1.48

 Reported

1.45

 Reports

1.44

Activations Density 0.163%

instances of the word "report" and its variations, suggesting a focus on reporting information or findings within texts

"report" or "reported"

reporting of findings

No Comments

No Known Activations