INDEX

Explanations

specific scientific and medical terms related to various topics such as biology, chemistry, and healthcare

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

organizations, places, and scientific terms

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

PerformLayout

-0.61

ambién

-0.57

StoryboardSegue

-0.54

InjectAttribute

-0.54

ErrUnexpectedEOF

-0.51

hilangan

-0.51

 commendable

-0.50

GOTREF

-0.50

aarrggbb

-0.49

 dominates

-0.48

POSITIVE LOGITS

-------------</

0.52

Pautan

0.38

 történ

0.34

 ويكيميديا

0.34

════

0.32

gebob

0.32

 հղումներ

0.31

utilisons

0.31

)=-\

0.31

 orquí

0.30

Activations Density 0.112%

specific scientific and medical terms related to various topics such as biology, chemistry, and healthcare

organizations, places, and scientific terms

No Comments

No Known Activations