INDEX

Explanations

terms related to programming constructs and structures in code

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

Code snippets or programming terms

np_acts-logits-general · gemini-2.0-flash

code namespaces and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

__(/*!

-0.52

}^{+\

-0.52

 biologie

-0.51

tieth

-0.51

OSO

-0.51

화

-0.50

website

-0.49

}}_

-0.48

 Acosta

-0.48

 internetowa

-0.47

POSITIVE LOGITS

::

1.76

・

0.90

::

0.88

::{

0.82

->

0.77

•

0.73

ValueStyle

0.72

::::

0.70

::~

0.69

 незавершена

0.68

Activations Density 0.102%

terms related to programming constructs and structures in code

Code snippets or programming terms

code namespaces and types

No Comments

No Known Activations