INDEX

Explanations

code-related syntax and programming constructs, particularly error handling and assembly attributes

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

or phrases followed by parentheses

np_acts-logits-general · gemini-2.0-flash

code identifiers and attributes

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

 kasarigan

-0.58

ară

-0.58

anyahu

-0.56

riwal

-0.55

Становништво

-0.53

TextNode

-0.53

InstanceState

-0.51

 optik

-0.50

-0.49

COLN

-0.49

POSITIVE LOGITS

 ModelExpression

1.30

webElementXpaths

1.19

 تضيفلها

1.17

Personensuche

1.17

UnusedPrivate

1.12

"}";

1.04

BibitemShut

1.03

LookAnd

1.01

)";

1.00

]})

1.00

Activations Density 0.367%

code-related syntax and programming constructs, particularly error handling and assembly attributes

or phrases followed by parentheses

code identifiers and attributes

No Comments

No Known Activations