INDEX

Explanations

mentions of "bed," including variations and contexts related to beds

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

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

tvguidetime

-0.90

MemoryWarning

-0.86

 متعلقه

-0.85

DockStyle

-0.82

ViewFeatures

-0.82

AsUp

-0.79

AxisAlignment

-0.79

 AssemblyCulture

-0.79

Cyfeiriadau

-0.78

 kasarigan

-0.70

POSITIVE LOGITS

 beds

0.71

 Beds

0.69

Bed

0.66

Beds

0.65

chamber

0.64

Bed

0.64

beds

0.63

BED

0.61

ridden

0.60

 mattresses

0.59

Activations Density 0.046%

mentions of "bed," including variations and contexts related to beds

No Comments

No Known Activations