INDEX

Explanations

phrases related to influential figures and their actions

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

Follows introductory words or phrases

np_acts-logits-general · gemini-2.0-flash

clause starters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ErrIntOverflow

-0.44

جغرافيا

-0.38

 Roskov

-0.35

 nemlig

-0.35

Jereo

-0.34

multer

-0.34

RTLD

-0.33

BeginContext

-0.33

basicConfig

-0.33

oa̍t

-0.32

POSITIVE LOGITS

 שוליים

0.59

LabelTagHelper

0.53

 فريبيس

0.51

RenderAtEndOf

0.51

]")]

0.50

AddTagHelper

0.50

XmlAccessorType

0.49

ViewInit

0.48

 defoli

0.48

InjectAttribute

0.47

Activations Density 3.460%

phrases related to influential figures and their actions

Follows introductory words or phrases

clause starters

No Comments

No Known Activations