INDEX

Explanations

prepositions and conjunctions in various contexts

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

preposition followed by article or noun

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

 kotlinx

-0.35

meist

-0.33

 dira

-0.31

 lienzo

-0.31

 hombros

-0.31

 continuidad

-0.31

umque

-0.31

pośred

-0.31

 nguoi

-0.31

 except

-0.30

POSITIVE LOGITS

 ویکی‌پدی

0.68

PerformLayout

0.60

GEBURTSDATUM

0.60

 ExecuteAsync

0.56

+#+#

0.56

enumii

0.56

msgTypes

0.55

sizeCache

0.54

 jsPsych

0.53

Activations Density 0.067%

prepositions and conjunctions in various contexts

preposition followed by article or noun

No Comments

No Known Activations