INDEX

Explanations

instances of object creation in programming code

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

Followed by capitalized words and object instantiations

np_acts-logits-general · gemini-2.0-flash

declaring new objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

“

-0.51

com

-0.48

::

-0.47

<b>

-0.46

odem

-0.44

<strong>

-0.44

ase

-0.43

ud

-0.42

”

-0.42

And

-0.41

POSITIVE LOGITS

 باخ

0.84

 الحره

0.82

UserScript

0.81

CPtr

0.80

 externi

0.80

ExecuteReader

0.79

 חיצוניים

0.78

зулта

0.77

 فريبيس

0.76

 resourceCulture

0.75

Activations Density 0.088%

instances of object creation in programming code

Followed by capitalized words and object instantiations

declaring new objects

No Comments

No Known Activations