INDEX

Explanations

references to religious authority figures, particularly the term "Lord."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Bris

-0.70

ционной

-0.69

ebra

-0.67

ней

-0.67

SOLUTION

-0.66

EOL

-0.63

Bris

-0.63

 bris

-0.62

цій

-0.62

xer

-0.61

POSITIVE LOGITS

 Lords

1.30

 lords

1.24

 lord

1.08

 LORD

1.07

 Lord

1.05

 lordship

1.01

LORD

0.95

Lord

0.91

 Lordship

0.88

 Seigneur

0.84

Activations Density 0.090%

references to religious authority figures, particularly the term "Lord."

No Comments

No Known Activations