INDEX

Explanations

references to self-improvement and personal growth experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

っこう

-0.54

Personendaten

-0.51

Personensuche

-0.47

SpringBootTest

-0.46

렀

-0.46

detto

-0.44

 sauvages

-0.44

CrossRef

-0.44

 Intra

-0.43

]),

-0.43

POSITIVE LOGITS

 life

2.69

life

2.24

 Life

2.11

Life

2.09

 lives

2.07

 LIFE

2.06

LIFE

2.00

 жизни

1.89

 vida

1.84

 Leben

1.78

Activations Density 0.281%

references to self-improvement and personal growth experiences

No Comments

No Known Activations