INDEX

Explanations

URLs and references to online resources

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

True questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 Wach

-0.40

Ter

-0.39

Mer

-0.38

Sv

-0.38

fis

-0.38

 Fish

-0.38

Fin

-0.36

li

-0.36

inv

-0.35

 обла

-0.35

POSITIVE LOGITS

 miniaturka

0.77

genodigd

0.68

BibitemShut

0.61

 vectorielles

0.61

 EconPapers

0.61

archiwizowane

0.60

 ainfi

0.60

 незавершена

0.58

 anhänger

0.58

 halide

0.57

Activations Density 0.001%

URLs and references to online resources

True questions

No Comments

No Known Activations