INDEX

Explanations

negations and words indicating disagreement or denial

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

"No" followed by words indicating doubt or uncertainty

np_acts-logits-general · gemini-2.0-flash

no followed by clarification or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 متعلقه

-0.70

 számára

-0.68

ktır

-0.59

 trás

-0.56

 textStatus

-0.56

 Roskov

-0.56

колко

-0.56

 незавершена

-0.55

 refusé

-0.55

Bioaccumulative

-0.53

POSITIVE LOGITS

 matter

1.55

 wonder

1.05

 doubt

1.00

matter

0.97

 MATTER

0.92

 worries

0.89

Matter

0.89

 offense

0.89

 Matter

0.88

 longer

0.87

Activations Density 0.092%

negations and words indicating disagreement or denial

"No" followed by words indicating doubt or uncertainty

no followed by clarification or negation

No Comments

No Known Activations