INDEX

Explanations

terms related to public health professionals and decision-makers

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

professions and roles

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ră

-0.33

regler

-0.32

deli

-0.32

 sekali

-0.31

🩹

-0.31

 sneeze

-0.31

CHARACTER

-0.30

 intptr

-0.30

windowFixed

-0.29

 تانيه

-0.29

POSITIVE LOGITS

OGND

0.70

AutoScaleMode

0.70

 незавершена

0.66

protoimpl

0.65

 estadounid

0.52

ActionCreators

0.50

ﬅ

0.50

KommentareTeilen

0.49

 administrators

0.48

autorest

0.48

Activations Density 0.014%

terms related to public health professionals and decision-makers

professions and roles

No Comments

No Known Activations