INDEX

Explanations

information formatted as data points or coordinates

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

Numerical sequences and hexadecimal values

np_acts-logits-general · gemini-2.0-flash

numbers and code snippets

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}));

-0.63

AISSEE

-0.62

 DialogInterface

-0.58

 Приступљено

-0.56

 NgModule

-0.56

 Expédié

-0.56

ciutto

-0.55

цездатний

-0.53

ContentAlignment

-0.53

>-->

-0.52

POSITIVE LOGITS

ReusableCell

0.59

 Réponses

0.59

󠁢

0.58

WithFormat

0.52

########.

0.52

CppCodeGen

0.52

󠁮

0.51

 jScrollPane

0.51

InputBorder

0.50

 oublié

0.50

Activations Density 0.468%

information formatted as data points or coordinates

Numerical sequences and hexadecimal values

numbers and code snippets

No Comments

No Known Activations