INDEX

Explanations

instances of specific variable attributes or types within code snippets

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

5 to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 during

-0.45

For

-0.44

 entre

-0.42

 cờ

-0.39

 bulat

-0.39

bad

-0.39

↵↵

-0.39

határoz

-0.39

 section

-0.39

POSITIVE LOGITS

الحياه

0.96

styleType

0.79

AddTagHelper

0.77

Демографія

0.76

ksikon

0.75

ValueStyle

0.74

')")

0.73

Obrázky

0.72

DoubleQuotes

0.72

 CURIAM

0.72

Activations Density 0.001%

instances of specific variable attributes or types within code snippets

5 to

No Comments

No Known Activations