INDEX

Explanations

phrases related to user account actions and alerts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

NamedQuery

-0.50

endcsname

-0.47

InMillis

-0.45

Xna

-0.45

 calls

-0.44

execSQL

-0.44

封面

-0.44

 bulunabilir

-0.43

 Unsc

-0.43

довал

-0.43

POSITIVE LOGITS

GEBURTSDATUM

0.84

 autorytatywna

0.83

 الحره

0.78

 Савезне

0.76

 Roskov

0.74

 beginnetje

0.71

 ComVisible

0.70

Autoritní

0.67

uxxxx

0.65

хьтан

0.64

Activations Density 0.418%

phrases related to user account actions and alerts

No Comments

No Known Activations