INDEX

Explanations

specific terms that pertain to cause-and-effect relationships or conditions

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

prepositions and conjunctions

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nämlich

-0.36

Gambas

-0.32

平

-0.31

TheReal

-0.30

 ErrIntOverflow

-0.28

hin

-0.28

 detailsLots

-0.27

fil

-0.27

multer

-0.26

 المن

-0.26

POSITIVE LOGITS

 שוליים

0.90

RenderAtEndOf

0.78

Personensuche

0.76

PreferredItem

0.72

WithIOException

0.69

'{@

0.66

CloseOperation

0.66

 initComponents

0.65

 فريبيس

0.65

AddTagHelper

0.64

Activations Density 0.218%

specific terms that pertain to cause-and-effect relationships or conditions

prepositions and conjunctions

No Comments

No Known Activations