INDEX

Explanations

programming terms and constructs related to data structures and types

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

Keywords following "type" or ":"

np_acts-logits-general · gemini-2.0-flash

identifying types: IO, Array, string, INT

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

<bos>

-0.49

yeni

-0.49

 StatelessWidget

-0.47

ViewFeatures

-0.47

casila

-0.46

ịch

-0.46

autoconfigure

-0.45

 inilah

-0.43

preduce

-0.42

atih

-0.42

POSITIVE LOGITS

expandindo

0.78

IndentedString

0.67

 pleaſure

0.64

.*")]

0.63

]--;

0.60

KURZBESCHREIBUNG

0.59

Geplaatst

0.59

 foon

0.58

 sóc

0.58

 Monfieur

0.58

Activations Density 0.477%

programming terms and constructs related to data structures and types

Keywords following "type" or ":"

identifying types: IO, Array, string, INT

No Comments

No Known Activations