INDEX

Explanations

terms related to "inter," indicating a focus on interactions and relationships

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

chtigkeit

-0.79

 végétale

-0.75

 Lightboxes

-0.74

ActionCreators

-0.69

 Smarty

-0.68

toJson

-0.68

httphttps

-0.67

Sådan

-0.66

GOTREF

-0.66

 bygga

-0.65

POSITIVE LOGITS

 inter

2.46

 Inter

2.41

Inter

2.31

 INTER

2.18

INTER

2.07

inter

2.06

 Inters

1.58

Inters

1.50

 interns

1.26

 Intere

1.24

Activations Density 0.086%

terms related to "inter," indicating a focus on interactions and relationships

No Comments

No Known Activations