INDEX

Explanations

references to specific individuals or organizations

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

"Smith"

np_acts-logits-general · gemini-2.0-flash

names like Smith or Joseph

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

 Duro

-0.69

 snippetHide

-0.68

 Allison

-0.67

MemoryWarning

-0.65

__(/*!

-0.64

 Darren

-0.63

 Otter

-0.63

 Stuttgart

-0.63

 Mila

-0.63

 Alton

-0.62

POSITIVE LOGITS

 Smith

2.22

Smith

2.08

 SMITH

1.95

 smith

1.77

SMITH

1.68

 Smiths

1.61

smith

1.46

 Smit

1.16

 Joseph

1.09

Sm

1.09

Activations Density 0.609%

references to specific individuals or organizations

"Smith"

names like Smith or Joseph

No Comments

No Known Activations