INDEX

Explanations

HTML tags and attributes

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

HTML tags and attributes

np_acts-logits-general · gemini-2.0-flash

opening tags

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 kasarigan

-0.84

 Cohn

-0.83

 calendriers

-0.75

Nye

-0.73

AsUp

-0.73

Nye

-0.73

ModelBuilder

-0.72

 Hays

-0.71

 henvisninger

-0.69

checkNotNull

-0.69

POSITIVE LOGITS

><

1.38

"><

1.11

;"><

0.93

="#"><

0.82

=""><

0.81

'><

0.80

ContextCompat

0.77

0.72

"<

0.71

Activations Density 0.090%

HTML tags and attributes

HTML tags and attributes

opening tags

No Comments

No Known Activations