INDEX

Explanations

terms related to medical or scientific processes and outcomes

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

political and institutional themes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ContentAsync

-0.69

PageIndex

-0.65

Tembelea

-0.64

ChildIndex

-0.62

ſelves

-0.60

esercito

-0.59

 purpoſe

-0.59

ſelf

-0.58

"]];

-0.58

)"),

-0.57

POSITIVE LOGITS

ThroughAttribute

0.82

IntoConstraints

0.65

Personendaten

0.59

ioutil

0.53

ConstraintMaker

0.49

 autorytatywna

0.48

MLLoader

0.47

 EconPapers

0.46

 mitt

0.46

شت

0.45

Activations Density 0.940%

terms related to medical or scientific processes and outcomes

followed by prepositions

political and institutional themes

No Comments

No Known Activations