INDEX

Explanations

terms related to legislation and acts focused on discrimination and safety regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Explanation

-0.41

efte

-0.41

 reti

-0.40

hon

-0.38

andan

-0.37

 상세

-0.37

ുറ

-0.37

pl

-0.37

 chefe

-0.36

ServiceImpl

-0.36

POSITIVE LOGITS

Act

1.00

 Мексичка

0.88

 BrowserModule

0.85

 /\.(

0.84

 Normdatei

0.83

SBATCH

0.82

EnableWeb

0.79

StoryboardSegue

0.79

-------------</

0.79

ArrowToggle

0.77

Activations Density 0.673%

terms related to legislation and acts focused on discrimination and safety regulations

No Comments

No Known Activations