INDEX

Explanations

structured data or functions related to programming concepts

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

Code snippets with special characters

np_acts-logits-general · gemini-2.0-flash

code delimiters like ( { <

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 MainAxisSize

-0.76

DispatchToProps

-0.66

GIVEREF

-0.64

StoryboardSegue

-0.61

UnusedPrivate

-0.60

EndGlobalSection

-0.58

]")]

-0.58

QMetaType

-0.56

->___

-0.55

AccessorTable

-0.54

POSITIVE LOGITS

`(

0.59

`<

0.55

 misfortune

0.52

`${

0.52

SequentialGroup

0.51

`{

0.51

'{

0.49

<<<

0.49

0.47

Activations Density 0.083%

structured data or functions related to programming concepts

Code snippets with special characters

code delimiters like ( { <

No Comments

No Known Activations