INDEX

Explanations

URLs and web domain references

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

domain names / url path separators

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

Distribuzione

-0.57

 متعلقه

-0.50

 circ

-0.50

IsContent

-0.50

 intStringLen

-0.48

fillType

-0.47

博物

-0.47

stęp

-0.47

 الاطلاع

-0.46

ndig

-0.46

POSITIVE LOGITS

 InputDecoration

0.88

Datuak

0.87

kuuta

0.73

 habet

0.71

 ujednoznacz

0.69

rungsseite

0.68

HostException

0.66

 izle

0.65

 quæ

0.64

 تانيه

0.60

Activations Density 0.037%

URLs and web domain references

domain names / url path separators

No Comments

No Known Activations