INDEX

Explanations

references to specific individuals and their familial connections

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

Last names starting with prefixes

np_acts-logits-general · gemini-2.0-flash

people's names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Diſ

-0.95

 Perſ

-0.91

 Reſ

-0.88

 Houſe

-0.88

 Conſ

-0.86

 Anſ

-0.84

 Inſ

-0.81

 abſ

-0.81

 Beſ

-0.78

uſ

-0.77

POSITIVE LOGITS

✨:

0.73

 Smith

0.73

De

0.70

 Johnson

0.67

Mc

0.66

 White

0.66

 Green

0.65

Le

0.64

 Brown

0.63

Activations Density 0.781%

references to specific individuals and their familial connections

Last names starting with prefixes

people's names

No Comments

No Known Activations