INDEX

Explanations

instances of sitting or standing actions

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

aarrggbb

-0.76

 estimés

-0.75

 Taktlose

-0.69

WireFormatLite

-0.68

 Италијани

-0.66

 estekak

-0.66

 ***!

-0.65

NameInMap

-0.64

principalTable

-0.63

IUrlHelper

-0.63

POSITIVE LOGITS

 motionless

0.69

 alone

0.58

 idle

0.56

 waiting

0.56

 beside

0.55

 facing

0.54

 holding

0.54

 upright

0.53

 outside

0.53

 still

0.53

Activations Density 0.137%

instances of sitting or standing actions

No Comments

No Known Activations