INDEX

Explanations

punctuation marks, particularly periods

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

0 followed by x or user

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

 незавершена

-0.67

TestingModule

-0.65

TemporalType

-0.59

 StatefulWidget

-0.58

saraba

-0.55

 مشين

-0.54

PickerController

-0.53

 EconPapers

-0.53

 contextLoads

-0.52

 дописавши

-0.52

POSITIVE LOGITS

 little

0.38

aClass

0.38

 bitterness

0.36

 caneta

0.36

 chronological

0.36

 propOrder

0.35

 surpresa

0.35

 vergüenza

0.35

 discreet

0.35

 obserw

0.35

Activations Density 0.000%

punctuation marks, particularly periods

0 followed by x or user

No Comments

No Known Activations