INDEX

Explanations

programming notations, particularly those related to image handling and structure definitions in code

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

Mathematical formulas with vertical lines

np_acts-logits-general · gemini-2.0-flash

math or food items like bagels

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

 Sjö

-0.48

hadap

-0.48

клопе

-0.46

 Lari

-0.45

 Fonten

-0.43

 Bradshaw

-0.42

 Verhält

-0.41

 Brun

-0.41

 impresa

-0.41

Abp

-0.41

POSITIVE LOGITS

3.28

0.94

0.93

[*]

0.80

0.69

########.

0.68

0.66

0.60

 CreateTagHelper

0.59

0.56

Activations Density 0.049%

programming notations, particularly those related to image handling and structure definitions in code

Mathematical formulas with vertical lines

math or food items like bagels

No Comments

No Known Activations