INDEX

Explanations

references to medal placements and rankings in competitive events

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

medal or podium finish

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

IUrlHelper

-0.53

 protoimpl

-0.52

WithIOException

-0.50

 Wiktionnaire

-0.49

issipp

-0.49

Transkript

-0.47

ᅠ

-0.45

Jeografia

-0.45

raits

-0.44

 transfieras

-0.44

POSITIVE LOGITS

aarrggbb

0.49

AnchorTagHelper

0.40

🥉

0.38

readystatechange

0.37

 оказыва

0.35

 jegy

0.35

 blessé

0.34

 inesperado

0.34

 nuages

0.34

 alternativo

0.34

Activations Density 0.006%

references to medal placements and rankings in competitive events

medal or podium finish

No Comments

No Known Activations