INDEX

Explanations

references to data structures and their manipulations in programming

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

`<start_of_turn>` user

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

 autoridad

-0.35

 jueces

-0.35

 Taktlose

-0.34

XmlAccessType

-0.33

 juiz

-0.32

 autoridade

-0.31

 propOrder

-0.31

 fronteras

-0.30

 dziś

-0.30

 Tiefe

-0.30

POSITIVE LOGITS

bootstrapcdn

0.51

(&:

0.50

rungsseite

0.49

andoah

0.49

nagem

0.49

berman

0.48

 holo

0.47

raborty

0.47

 FetchType

0.46

bux

0.46

Activations Density 0.011%

references to data structures and their manipulations in programming

`<start_of_turn>` user

No Comments

No Known Activations