INDEX

Explanations

specific punctuation marks and their occurrences in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

exitRule

-0.52

ArgsConstructor

-0.51

 esternos

-0.49

RenderAtEndOf

-0.45

extAlignment

-0.45

 متعلقه

-0.44

 InputDecoration

-0.44

stateProvider

-0.43

HomeAsUpEnabled

-0.42

</>

-0.42

POSITIVE LOGITS

 EconPapers

0.52

Autoritní

0.46

 kaarangay

0.45

Tē

0.41

पया

0.40

تقاوى

0.40

 appelez

0.40

 utafitiHapana

0.40

hyrchwyd

0.39

 Савезне

0.38

Activations Density 0.007%

specific punctuation marks and their occurrences in various contexts

No Comments

No Known Activations