INDEX

Explanations

references to military forts and installations

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

"Fort" followed by a place name

np_acts-logits-general · gemini-2.0-flash

Fort followed by place names

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

 незавершена

-0.82

Bub

-0.78

 дописавши

-0.78

ệc

-0.75

ainville

-0.73

adaptiveStyles

-0.72

KEYCODE

-0.72

ergies

-0.71

ponses

-0.71

pacs

-0.71

POSITIVE LOGITS

 FORT

0.98

 Fort

0.94

Fort

0.85

fort

0.81

 fort

0.74

FORT

0.69

 Ross

0.60

 Forte

0.59

Ft

0.56

 forts

0.56

Activations Density 0.284%

references to military forts and installations

"Fort" followed by a place name

Fort followed by place names

No Comments

No Known Activations