INDEX

Explanations

language related to planning and organization in various contexts, particularly in reference to future actions or sessions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

astify

-0.68

 يتيمه

-0.68

GOTREF

-0.64

 Waray

-0.64

migrationBuilder

-0.62

ValueStyle

-0.61

TagMode

-0.61

ódó

-0.60

FXMLLoader

-0.60

 initComponents

-0.59

POSITIVE LOGITS

 covers

1.68

 covered

1.61

 covering

1.57

 cover

1.51

 Covers

1.48

 discuss

1.48

 discusses

1.44

 discussing

1.41

covers

1.39

Covers

1.38

Activations Density 0.606%

language related to planning and organization in various contexts, particularly in reference to future actions or sessions

No Comments

No Known Activations