INDEX

Explanations

comments and evaluations related to personal experiences and preferences

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

mediocre or average quality

np_acts-logits-general · gemini-2.0-flash

moderate assessments

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

 irresistible

-0.75

 incredible

-0.72

 unglaub

-0.71

 unbelievable

-0.70

 unbelievably

-0.69

 enormous

-0.66

 unimaginable

-0.66

incredible

-0.66

 unprecedented

-0.65

 totalité

-0.63

POSITIVE LOGITS

 somewhat

1.14

 moderately

1.13

somewhat

1.06

 decent

1.02

 decently

1.01

 Somewhat

1.00

 slightly

0.97

 fairly

0.96

 reasonably

0.93

 mildly

0.93

Activations Density 0.395%

comments and evaluations related to personal experiences and preferences

mediocre or average quality

moderate assessments

No Comments

No Known Activations