INDEX

Explanations

phrases related to conflicts of interest in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

$_['

-0.86

 auroit

-0.85

 étoit

-0.84

 estoppel

-0.80

Personendaten

-0.79

 lourdes

-0.79

 pronti

-0.79

 Rifles

-0.78

 ceramica

-0.78

 OnInit

-0.77

POSITIVE LOGITS

λ

0.93

lambda

0.89

 lambda

0.82

mybatisplus

0.81

dock

0.77

 spectra

0.73

 Fisch

0.72

 Spectrum

0.72

Brigitte

0.72

 Jackson

0.72

Activations Density 0.162%

phrases related to conflicts of interest in research

No Comments

No Known Activations