INDEX

Explanations

elements related to dialogue and character interactions in a story

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

Actions performed by royalty characters

np_acts-logits-general · gemini-2.0-flash

gestures and actions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

NameInMap

-0.95

UnknownFieldSet

-0.75

AndEndTag

-0.73

AccessorTable

-0.70

 виправивши

-0.66

opsida

-0.65

ViewImports

-0.61

urally

-0.59

 ujednoznacz

-0.58

 orgánica

-0.58

POSITIVE LOGITS

 gest

0.72

 pointing

0.71

 gaze

0.65

 smile

0.64

 pointed

0.64

 smiled

0.62

 stare

0.62

 gesture

0.62

pointing

0.61

gest

0.60

Activations Density 0.161%

elements related to dialogue and character interactions in a story

Actions performed by royalty characters

gestures and actions

No Comments

No Known Activations