INDEX

Explanations

references to specific data formats or categories within a structured context

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

Text formatted as tables

np_acts-logits-general · gemini-2.0-flash

to the 2000

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 saites

-0.73

tanleria

-0.64

GeneratedValue

-0.62

 Italijani

-0.55

']")

-0.54

GeoNames

-0.51

 iconTwitter

-0.50

ılacak

-0.50

="../

-0.48

сюда

-0.48

POSITIVE LOGITS

__':

0.87

verwijspagina

0.86

__':

0.71

__":

0.70

ContentAsync

0.65

Scénario

0.64

HasForeignKey

0.63

SequentialGroup

0.62

igshid

0.58

 rêver

0.57

Activations Density 0.629%

references to specific data formats or categories within a structured context

Text formatted as tables

to the 2000

No Comments

No Known Activations