INDEX

Explanations

the word "little" in various contexts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kään

-0.39

ként

-0.38

 tyres

-0.38

 bañ

-0.36

 demnach

-0.35

 aérienne

-0.34

 Diseño

-0.33

 tüm

-0.33

 opérateur

-0.33

Biomass

-0.33

POSITIVE LOGITS

little

1.07

 little

1.05

 LITTLE

0.98

Little

0.94

addPreferredGap

0.88

 Little

0.87

LITTLE

0.85

addGap

0.78

 bisschen

0.76

 Littleton

0.76

Activations Density 0.006%

the word "little" in various contexts

No Comments

No Known Activations