INDEX

Explanations

discussions around detection and residual analysis in systems

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

"All" followed by "the," or "other."

np_acts-logits-general · gemini-2.0-flash

other / others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 <=",

-0.46

crizione

-0.44

czegó

-0.44

ljen

-0.41

Personensuche

-0.40

ált

-0.39

ایا

-0.39

áni

-0.39

pezi

-0.38

COUVER

-0.38

POSITIVE LOGITS

 other

3.80

other

3.29

Other

2.98

 Other

2.92

 autres

2.89

autres

2.88

 otros

2.82

 otras

2.77

 OTHER

2.77

 outras

2.69

Activations Density 1.702%

discussions around detection and residual analysis in systems

"All" followed by "the," or "other."

other / others

No Comments

No Known Activations