INDEX

Explanations

terms related to consent and ethical approval in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 rich

-0.65

ToTable

-0.61

 חיצוניים

-0.60

 counter

-0.59

tra

-0.58

ड़ी

-0.57

agaimana

-0.57

bar

-0.57

baiki

-0.56

 Cutler

-0.56

POSITIVE LOGITS

 consent

3.23

 Consent

2.92

consent

2.77

Consent

2.67

 consents

2.27

 consentement

2.03

 consentimiento

2.01

 consented

1.99

 consenting

1.83

 permission

1.68

Activations Density 0.120%

terms related to consent and ethical approval in research contexts

No Comments

No Known Activations