INDEX

Explanations

phrases and terms related to programming and coding concepts

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

Follows user input

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 resourceCulture

-0.62

Tikang

-0.60

 تضيفلها

-0.54

 hindsight

-0.53

الدراسه

-0.53

writ

-0.52

neath

-0.51

各式

-0.50

styleType

-0.50

 έχ

-0.50

POSITIVE LOGITS

 itſelf

0.54

 juſt

0.52

 Houſe

0.47

 deſt

0.47

 Monfieur

0.46

 Majefty

0.45

 poffible

0.45

 esqueleto

0.45

 Reſ

0.44

 uſed

0.44

Activations Density 0.023%

phrases and terms related to programming and coding concepts

Follows user input

No Comments

No Known Activations