INDEX

Explanations

terms related to various forms of constraints and limitations

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

permanence or duration

np_acts-logits-general · gemini-2.0-flash

permanent and chronic states

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

ApiModel

-0.49

tivität

-0.47

 innocence

-0.46

tops

-0.46

žių

-0.44

Население

-0.43

valla

-0.43

 noses

-0.43

 occidentale

-0.43

 Auft

-0.43

POSITIVE LOGITS

 permanent

2.12

permanent

1.86

 permanently

1.86

Permanent

1.70

 Permanent

1.70

 PERMAN

1.62

 permanente

1.53

 Perman

1.48

 dauer

1.44

perman

1.44

Activations Density 0.663%

terms related to various forms of constraints and limitations

permanence or duration

permanent and chronic states

No Comments

No Known Activations