INDEX

Explanations

definite and indefinite articles in various contexts

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

a/an followed by 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

gerufen

-0.38

SourceChecksum

-0.35

DMETHOD

-0.35

 Italijanski

-0.35

(!__

-0.35

RTHOOK

-0.32

tagHelper

-0.32

 šķ

-0.31

 Мексичка

-0.31

 الرياضيه

-0.31

POSITIVE LOGITS

 ſehr

0.59

 deſſen

0.58

 ſeinen

0.56

hilt

0.56

Biographie

0.56

 dieſen

0.55

 ſeiner

0.54

 zwiſchen

0.54

 dieſem

0.54

rungsseite

0.54

Activations Density 0.010%

definite and indefinite articles in various contexts

a/an followed by noun

No Comments

No Known Activations