INDEX

Explanations

references to the act of checking in and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Референце

-0.51

alanta

-0.49

MainFrame

-0.48

 gerek

-0.47

flüs

-0.46

 Covered

-0.46

 riscos

-0.46

باد

-0.45

 Zuid

-0.44

 catalyzed

-0.44

POSITIVE LOGITS

checkin

1.02

CheckIn

0.97

 EClass

0.85

GEBURTSDATUM

0.82

 surla

0.78

uxxxx

0.78

setVerticalGroup

0.77

 punches

0.73

 Punch

0.72

 punching

0.72

Activations Density 0.149%

references to the act of checking in and related terminology

No Comments

No Known Activations