INDEX

Explanations

elements related to exams, evaluations, and responses in various contexts

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

following "the"

np_acts-logits-general · gemini-2.0-flash

debt levelgenetic driftMercury informwater potentialrow of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 arcilla

-0.38

Oneof

-0.37

kep

-0.36

 препратки

-0.36

舺

-0.35

RegistryLite

-0.35

iski

-0.35

Mot

-0.35

Para

-0.34

 cref

-0.34

POSITIVE LOGITS

 snippetHide

0.65

 informée

0.65

 StatelessWidget

0.60

0.59

 surla

0.58

Kaieteur

0.57

 Infórmanos

0.55

 noDo

0.53

Życiorys

0.53

tvguidetime

0.51

Activations Density 0.787%

elements related to exams, evaluations, and responses in various contexts

following "the"

debt levelgenetic driftMercury informwater potentialrow of

No Comments

No Known Activations