INDEX

Explanations

references to qualities and attributes of objects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

HomeAsUpEnabled

-0.73

verwijspagina

-0.72

 jdbcTemplate

-0.70

脚注の使い方

-0.68

 whoſe

-0.67

SequentialGroup

-0.66

ImageIO

-0.65

 myſelf

-0.65

 pleaſure

-0.64

enumii

-0.63

POSITIVE LOGITS

 characteristics

1.73

characteristics

1.48

 Characteristics

1.46

 characteristic

1.44

 traits

1.41

Characteristics

1.37

 qualities

1.30

 Eigenschaften

1.26

 caractéristique

1.23

 properties

1.23

Activations Density 0.350%

references to qualities and attributes of objects or concepts

No Comments

No Known Activations