INDEX

Explanations

code constructs and programming language patterns indicative of function definitions and variable declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 clearColor

-0.62

 viewDidLoad

-0.58

 StyleSheet

-0.55

 forState

-0.51

 MatDialog

-0.51

unittest

-0.50

 scanf

-0.50

 OnInit

-0.48

 lateinit

-0.48

Malloc

-0.48

POSITIVE LOGITS

StoryboardSegue

0.78

QMetaType

0.69

setVerticalGroup

0.68

+#+#

0.66

 مشين

0.63

tagHelperRunner

0.62

拗

0.62

 egentligen

0.61

Przypisy

0.60

antaranya

0.59

Activations Density 0.160%

code constructs and programming language patterns indicative of function definitions and variable declarations

No Comments

No Known Activations