INDEX

Explanations

specific references to influential figures or themes relating to media and public perception

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

unpublished information or revelations

np_acts-logits-general · gemini-2.0-flash

revealing or unpublished information

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

 Roskov

-0.57

 beginnetje

-0.57

 cappuccio

-0.55

 venons

-0.52

 identité

-0.51

 nationalen

-0.51

Identyfik

-0.51

 scorso

-0.51

+#+#

-0.51

parametrize

-0.50

POSITIVE LOGITS

 insiders

0.79

 insider

0.76

 revealing

0.71

 revelations

0.71

 unpublished

0.70

 reveal

0.69

 revealed

0.68

 reconstructed

0.68

 biographer

0.68

insider

0.66

Activations Density 0.461%

specific references to influential figures or themes relating to media and public perception

unpublished information or revelations

revealing or unpublished information

No Comments

No Known Activations