INDEX

Explanations

references to pop-up messages or alerts in programming contexts

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

 esternos

-0.89

 Meksiku

-0.82

 "..\..\..\

-0.81

 الحره

-0.77

__(/*!

-0.76

✨:

-0.75

ciences

-0.75

 ligiloj

-0.74

Brainz

-0.74

queryInterface

-0.72

POSITIVE LOGITS

LENGTH

0.78

VersionUID

0.68

makeText

0.62

BufferException

0.55

 MessageBoxIcon

0.53

GraphicsUnit

0.51

 getSystem

0.47

KEYCODE

0.46

SHORT

0.45

EndTag

0.45

Activations Density 0.021%

references to pop-up messages or alerts in programming contexts

No Comments

No Known Activations