INDEX

Explanations

occurrences of the word "print" in various contexts

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

print or books

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

 companyId

-0.52

NECTION

-0.48

hoppers

-0.47

jenige

-0.46

 Boul

-0.44

 deviceId

-0.44

 equipa

-0.44

uevas

-0.43

 categoryId

-0.41

 customerId

-0.41

POSITIVE LOGITS

 print

2.16

print

1.52

 Print

1.16

 PRINT

1.12

 prints

1.00

Print

0.91

プリント

0.84

PRINT

0.73

 Prints

0.68

 printed

0.68

Activations Density 0.004%

occurrences of the word "print" in various contexts

print or books

No Comments

No Known Activations