INDEX

Explanations

patterned phrases and references, particularly focusing on citations and statistical terms in academic contexts

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

Citations and references

np_acts-logits-general · gemini-2.0-flash

van, vin, cut

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

EDEFAULT

-0.57

NewGuid

-0.55

—

-0.53

cumulative

-0.52

 Weise

-0.52

 grazia

-0.49

 poursu

-0.49

 ExecuteAsync

-0.49

 ویکی‌پدیا

-0.48

 videre

-0.47

POSITIVE LOGITS

VN

0.74

mybatisplus

0.67

VJ

0.65

 autorytatywna

0.65

VY

0.63

 EconPapers

0.63

 estimés

0.61

AccessorTable

0.61

VV

0.61

Demografia

0.59

Activations Density 0.250%

patterned phrases and references, particularly focusing on citations and statistical terms in academic contexts

Citations and references

van, vin, cut

No Comments

No Known Activations