INDEX

Explanations

instances of intent or deliberation in actions or statements

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

intention or purpose

np_acts-logits-general · gemini-2.0-flash

words indicating deliberate action

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

 للمعارف

-0.87

✨:

-0.81

adaptiveStyles

-0.79

 AssemblyTitle

-0.77

ſelves

-0.76

ſelf

-0.76

wiſe

-0.71

hdashline

-0.71

]<<"

-0.71

ItemBackground

-0.70

POSITIVE LOGITS

ly

0.58

 increase

0.53

oa̍t

0.52

ServiceModel

0.51

 superior

0.51

 olarak

0.50

cut

0.49

basicConfig

0.49

 הזה

0.48

ombat

0.48

Activations Density 0.295%

instances of intent or deliberation in actions or statements

intention or purpose

words indicating deliberate action

No Comments

No Known Activations