INDEX

Explanations

references to specific individuals or entities associated with the term "Sch" followed by various suffixes

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

Tokens starting with "Sch"

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

tableFuture

-0.62

 tartalomajánló

-0.53

 IBOutlet

-0.48

litten

-0.47

nitten

-0.45

luß

-0.44

 partly

-0.44

 Laut

-0.43

 Orte

-0.43

ijnt

-0.42

POSITIVE LOGITS

Sch

0.69

Sch

0.69

sch

0.65

SCH

0.57

 referenties

0.53

Scho

0.52

 ſch

0.51

StoreMessageInfo

0.48

 telefónica

0.48

:✨

0.45

Activations Density 0.092%

references to specific individuals or entities associated with the term "Sch" followed by various suffixes

Tokens starting with "Sch"

No Comments

No Known Activations