INDEX

Explanations

character names or identifiers within the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 חיצוניים

-0.68

webElement

-0.58

!*\

-0.55

.*")]

-0.54

Autoritní

-0.53

ništvo

-0.53

ChildScrollView

-0.52

Aholisi

-0.51

orteur

-0.50

EndProject

-0.49

POSITIVE LOGITS

BufferException

0.59

 quitted

0.58

 BoxFit

0.57

 typhoid

0.57

epam

0.54

@}

0.53

AxisAlignment

0.53

leyeb

0.53

 Yugos

0.53

 Chriftian

0.52

Activations Density 0.069%

character names or identifiers within the text

No Comments

No Known Activations