INDEX

Explanations

terms and phrases related to geographical features and natural landscapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

GraphicsUnit

-0.70

UnusedPrivate

-0.66

homonymie

-0.63

webElement

-0.60

MLLoader

-0.59

 uLocal

-0.59

WriteBarrier

-0.57

ListItemIcon

-0.56

 getItemCount

-0.55

 Infórmanos

-0.54

POSITIVE LOGITS

side

0.79

 biome

0.65

ides

0.63

 scenery

0.60

 region

0.59

 edge

0.57

 path

0.57

SceneManagement

0.57

 area

0.55

scape

0.55

Activations Density 0.237%

terms and phrases related to geographical features and natural landscapes

No Comments

No Known Activations