INDEX

Explanations

terms related to relationships and connections

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

that come before "to," when "to" indicates a relationship

np_acts-logits-general · gemini-2.0-flash

relation between things

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 تضيفلها

-0.86

GraphicsUnit

-0.80

DockStyle

-0.77

 BoxDecoration

-0.75

 سكانية

-0.73

 Hamm

-0.73

 Woodbury

-0.72

 crystallization

-0.71

 Winn

-0.71

 Magdeburg

-0.70

POSITIVE LOGITS

 relating

0.92

 relations

0.91

 relation

0.91

 Relating

0.87

 RELATION

0.85

 relate

0.84

 relates

0.83

Relation

0.81

rel

0.81

Rel

0.79

Activations Density 0.159%

terms related to relationships and connections

that come before "to," when "to" indicates a relationship

relation between things

No Comments

No Known Activations