INDEX

Explanations

terms associated with confidentiality and supportive environments for individuals seeking help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

FTFY

-0.68

äft

-0.54

memoized

-0.53

 Sélectionnez

-0.53

quiao

-0.53

cellation

-0.52

 voodoo

-0.49

/>\

-0.49

 Divider

-0.49

ارة

-0.49

POSITIVE LOGITS

Personendaten

0.83

 forgiving

0.66

tolerant

0.63

Erreferentziak

0.61

nesty

0.59

 forgiven

0.59

 welcomes

0.59

 welcoming

0.58

 tolerance

0.58

 welcome

0.58

Activations Density 0.294%

terms associated with confidentiality and supportive environments for individuals seeking help

No Comments

No Known Activations