INDEX

Explanations

references to warfare and expressions of positivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 noqa

-0.87

ERVIS

-0.65

 viewDidLoad

-0.59

TRAILING

-0.59

Slf

-0.58

deepcopy

-0.58

roek

-0.57

aktor

-0.53

getWriter

-0.53

:✨

-0.53

POSITIVE LOGITS

 незавершена

0.78

 cherchés

0.74

Geografi

0.67

GEBURTSDATUM

0.66

 opposition

0.63

Nice

0.62

 Decorative

0.61

Beautiful

0.60

rungsseite

0.60

 opponents

0.59

Activations Density 0.192%

references to warfare and expressions of positivity

No Comments

No Known Activations