INDEX

Explanations

locations and geopolitical references

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

 surla

-0.56

nowu

-0.52

addCriterion

-0.51

 Puget

-0.50

 Nationalism

-0.48

gpl

-0.48

خواندن

-0.48

providedIn

-0.48

 HttpNotFound

-0.47

 gminy

-0.46

POSITIVE LOGITS

الحياه

0.65

ptonshire

0.56

 tempat

0.56

pta

0.56

에서

0.56

PLICATE

0.55

 ComVisible

0.54

ajuku

0.54

tonode

0.53

iana

0.52

Activations Density 0.458%

locations and geopolitical references

No Comments

No Known Activations