INDEX

Explanations

various mathematical notation and expressions, particularly related to parentheses and operations

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

Personensuche

-0.52

DebuggerNonUser

-0.50

]='\

-0.48

fromnode

-0.47

redit

-0.47

 apó

-0.44

REDIT

-0.44

Væ

-0.43

atisme

-0.43

 Scherer

-0.43

POSITIVE LOGITS

SourceChecksum

0.95

 nakalista

0.78

 getItemId

0.75

QMetaType

0.71

:✨

0.69

 autorytatywna

0.67

FunctionFlags

0.66

########.

0.65

Referanser

0.63

adaptiveStyles

0.63

Activations Density 0.577%

various mathematical notation and expressions, particularly related to parentheses and operations

No Comments

No Known Activations