INDEX

Explanations

references to graphical or visual elements in programming

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

SourceChecksum

-0.96

GEBURTSDATUM

-0.76

principalColumn

-0.71

róż

-0.70

 ErrIntOverflow

-0.67

 kasarigan

-0.65

(~(

-0.64

addCriterion

-0.64

:"-"`

-0.61

InjectAttribute

-0.60

POSITIVE LOGITS

Drawing

1.32

 Drawing

1.10

 drawing

0.95

drawing

0.91

Efq

0.90

djangoproject

0.83

 purpoſe

0.81

ſelf

0.81

 DRAWING

0.80

 drawings

0.79

Activations Density 0.005%

references to graphical or visual elements in programming

No Comments

No Known Activations