INDEX

Explanations

programming-related terminology and constructs, particularly those involved in error handling and data type manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$_['

-0.56

 geslacht

-0.54

-0.53

lo

-0.52

seende

-0.52

žo

-0.50

 snippetHide

-0.49

 beginnetje

-0.49

 NSCoder

-0.48

 Среди

-0.47

POSITIVE LOGITS

MigrationBuilder

0.78

DockStyle

0.69

TextWatcher

0.68

WaitGroup

0.66

prefixer

0.61

 MenuView

0.60

AutoresizingMask

0.60

 ContentValues

0.58

VersionUID

0.58

 SwiftUI

0.56

Activations Density 0.635%

programming-related terminology and constructs, particularly those involved in error handling and data type manipulation

No Comments

No Known Activations